© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2562
    Prev
    Next
    INDEX
    Explanations

    names that have the pattern 'qui' or 'vel'

    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
    48
    +0.07
    0.2%
    1464
    +0.07
    0.2%
    812
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.07
    0.07
    283
    +0.07
    0.02
    1363
    +0.07
    0.05
    Negative Logits
     hentai
    -1.52
     snoopy
    -1.32
     milf
    -1.31
     scrat
    -1.31
     waifu
    -1.29
     excru
    -1.28
     impra
    -1.27
     madonna
    -1.24
     increa
    -1.23
     emphat
    -1.23
    POSITIVE LOGITS
    qui
    1.84
    vat
    1.43
    Qui
    1.31
     Qui
    1.29
    QUI
    1.28
     qui
    1.20
    rome
    1.11
    Vat
    0.75
     كومونز
    0.73
    VAT
    0.72
    Activations Density 0.422%

    No Known Activations