© 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. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 11
    Prev
    Next
    INDEX
    Explanations

    many different types of punctuation and conversational fillers.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </caption>
    -0.91
    [])
    -0.88
    />";
    -0.87
    %");
    -0.86
    ]='\
    -0.84
    %"),
    -0.84
    )";
    -0.82
    ſelves
    -0.81
    "),
    -0.81
    ſelf
    -0.81
    POSITIVE LOGITS
     I
    1.48
    I
    1.19
     Maybe
    1.13
     maybe
    1.11
    Maybe
    1.05
     What
    1.02
     why
    1.01
     Why
    0.99
    What
    0.96
     what
    0.94
    Activations Density 4.601%

    No Known Activations