© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30015
    Prev
    Next
    INDEX
    Explanations

    the word "excess", sometimes followed by "of"

    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
    :+:
    -0.78
     "..\..\
    -0.77
     nahilalakip
    -0.70
    roxene
    -0.69
     Cly
    -0.67
    OfBirth
    -0.67
     חיצוניים
    -0.67
    ########.
    -0.65
     Larkin
    -0.65
    Serializable
    -0.65
    POSITIVE LOGITS
     excess
    1.13
     Excess
    1.13
    Excess
    1.06
    excess
    0.95
     excesses
    0.90
     Surplus
    0.78
     excès
    0.77
     adhé
    0.75
    ymce
    0.75
     Segovia
    0.73
    Activations Density 0.004%

    No Known Activations