© 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. 33
    Prev
    Next
    INDEX
    Explanations

    words or phrases used in a specific, technical or legal context.

    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
     ModelExpression
    -0.64
    IntoConstraints
    -0.63
     ſmall
    -0.61
     ſeveral
    -0.59
    Personensuche
    -0.59
     blessés
    -0.59
     Theſe
    -0.59
     uſe
    -0.58
     nuages
    -0.57
    ()].
    -0.57
    POSITIVE LOGITS
     is
    2.42
     has
    1.73
     does
    1.54
     can
    1.49
     makes
    1.38
     will
    1.38
     may
    1.38
     takes
    1.37
     gives
    1.37
     provides
    1.34
    Activations Density 6.017%

    No Known Activations