© 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. 90954
    Prev
    Next
    INDEX
    Explanations

    ives

    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
    ically
    -0.77
    ives
    -0.76
    ed
    -0.66
    reads
    -0.66
     whereof
    -0.65
    iest
    -0.59
    neling
    -0.58
    ecd
    -0.55
     billions
    -0.55
    ual
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.74
    ftagPool
    0.73
    AndEndTag
    0.66
    المناصب
    0.60
     Chwiliwch
    0.56
    stateProvider
    0.56
    abestanden
    0.54
    AutoresizingMask
    0.53
    Hozzáférés
    0.52
    cetes
    0.52
    Activations Density 0.112%

    No Known Activations