© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2570
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "sia" within longer words or phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1325
    +0.09
    0.2%
    1828
    +0.08
    0.2%
    545
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.06
    283
    +0.08
    0.02
    1363
    +0.07
    0.04
    Negative Logits
     augus
    -0.86
     antik
    -0.86
     kram
    -0.83
     mikrofon
    -0.81
     makro
    -0.80
     trist
    -0.80
     panik
    -0.79
     tork
    -0.77
     eier
    -0.76
     utop
    -0.75
    POSITIVE LOGITS
    sia
    1.25
    idd
    1.00
    uff
    0.90
     farsi
    0.79
     pylab
    0.74
     scal
    0.71
    giar
    0.70
    hamdu
    0.68
     smtplib
    0.65
     pymongo
    0.62
    Activations Density 0.346%

    No Known Activations