© 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. 22-RES-MATRYOSHKA-DC
    7. 2194
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with crime and investigations

    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.22.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.22.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
     surla
    -0.69
     متعلقه
    -0.63
    ]")]
    -0.63
    UserScript
    -0.58
     Alembic
    -0.56
     htons
    -0.56
    ⓘ
    -0.56
    rayage
    -0.55
     navideña
    -0.54
    poptosis
    -0.54
    POSITIVE LOGITS
     just
    0.66
     what
    0.63
     they
    0.63
    loroethene
    0.60
     there
    0.60
     you
    0.60
     everything
    0.59
     basically
    0.59
     everyone
    0.59
     it
    0.58
    Activations Density 3.071%

    No Known Activations