© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1237
    Prev
    Next
    INDEX
    Explanations

    SQLite

    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
    CE
    -0.77
    itative
    -0.58
    ce
    -0.56
    lite
    -0.55
    lites
    -0.51
    ual
    -0.48
    nos
    -0.48
    曖昧さ回避
    -0.47
    SharedCtor
    -0.46
     CE
    -0.45
    POSITIVE LOGITS
    endaftaran
    0.75
    atguigu
    0.71
    σιμοποι
    0.69
    InjectAttribute
    0.63
    PageIndex
    0.63
     Wiktionnaire
    0.63
     getItemCount
    0.59
     виправивши
    0.59
    gdala
    0.59
    DateUtils
    0.58
    Activations Density 0.135%

    No Known Activations