© 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. 6-RES-MATRYOSHKA-DC
    7. 836
    Prev
    Next
    INDEX
    Explanations

    commas followed by words that carry importance to the meaning of the sentence

    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
     يتيمه
    -0.83
    horabuena
    -0.76
    RectangleBorder
    -0.75
    ={({
    -0.73
     tallest
    -0.73
     صوتيه
    -0.71
     pleaf
    -0.70
    ggard
    -0.70
    valently
    -0.69
     Majefty
    -0.69
    POSITIVE LOGITS
    ScopeManager
    0.78
    enderror
    0.68
     will
    0.67
     is
    0.63
     has
    0.63
     were
    0.58
     was
    0.56
     are
    0.53
     that
    0.52
     can
    0.51
    Activations Density 0.794%

    No Known Activations