© 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. 124
    Prev
    Next
    INDEX
    Explanations

    code with names separated by underscores like "NG X"

    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
    zoni
    -0.39
     مشين
    -0.38
    zag
    -0.37
    cios
    -0.37
    etera
    -0.37
    zana
    -0.37
    zell
    -0.36
    usc
    -0.35
    iac
    -0.35
    aires
    -0.35
    POSITIVE LOGITS
    ST
    0.45
    ON
    0.45
    CH
    0.44
    OF
    0.44
    RE
    0.44
    AP
    0.43
    EN
    0.43
    DE
    0.43
    EC
    0.43
    ER
    0.42
    Activations Density 12.651%

    No Known Activations