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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 152
    Prev
    Next
    INDEX
    Explanations

    instances where the word "affirm" is mentioned quite strongly

    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
    1677
    +0.07
    0.2%
    1376
    +0.07
    0.2%
    735
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.07
    0.03
    1363
    +0.07
    0.03
    1905
    +0.07
    0.03
    Negative Logits
    fortawesome
    -0.59
    퀀
    -0.57
    /*
    -0.56
     fit
    -0.55
    يديو
    -0.54
    thenReturn
    -0.53
    Parcelize
    -0.51
     kit
    -0.51
     fits
    -0.50
     kits
    -0.50
    POSITIVE LOGITS
     affirm
    1.39
     affirmation
    1.33
     affirmed
    1.24
     disagre
    1.24
     shenan
    1.19
     affirms
    1.18
     affirming
    1.17
     emphat
    1.16
     Juf
    1.14
    Affirm
    1.13
    Activations Density 0.278%

    No Known Activations