© 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. 0-CLT-HP
    4. 38769
    Prev
    Next
    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drawing
    -0.42
    aktur
    -0.42
    OTTEN
    -0.40
    Composable
    -0.38
    karte
    -0.36
    sauce
    -0.36
    tasche
    -0.35
    unción
    -0.35
    stepping
    -0.34
    bibnamefont
    -0.34
    POSITIVE LOGITS
    <bos>
    1.30
     nahilalakip
    1.09
    ⓧ
    1.07
     متعلقه
    1.05
    LookAnd
    1.02
     autorytatywna
    0.98
     disambiguazione
    0.96
     ProtoMessage
    0.90
     חיצוניים
    0.88
     للمعارف
    0.86
    Activations Density 0.138%

    No Known Activations