© 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. 24-RES-MATRYOSHKA-DC
    7. 332
    Prev
    Next
    INDEX
    Explanations

    code comments or other documentation strings

    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.24.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.24.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
    .*;
    -0.64
    <eos>
    -0.63
     المعيارى
    -0.58
    !")
    -0.58
    saraba
    -0.57
    ✨:
    -0.57
    ViewFeatures
    -0.56
    )))));
    -0.56
    InjectAttribute
    -0.54
     thereupon
    -0.54
    POSITIVE LOGITS
     This
    0.92
     NOTE
    0.92
     Must
    0.84
     If
    0.83
    NOTE
    0.83
     Used
    0.82
     Allows
    0.82
     TODO
    0.81
     Returns
    0.80
     Note
    0.79
    Activations Density 1.939%

    No Known Activations