© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1207
    Prev
    Next
    INDEX
    Explanations

    the string "Gra_ci", where _ is any character

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.80
     Kessel
    -0.73
    pośred
    -0.72
     Genoa
    -0.71
     souple
    -0.71
     Pog
    -0.70
     espagne
    -0.70
     Té
    -0.69
    🤣🤣
    -0.69
     extré
    -0.69
    POSITIVE LOGITS
     Gra
    2.41
    Gra
    2.34
    gra
    2.23
     gra
    2.23
     GRA
    1.84
     GR
    1.77
    GR
    1.59
     gr
    1.56
     grad
    1.55
     Graff
    1.53
    Activations Density 0.654%

    No Known Activations