© 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. 1209
    Prev
    Next
    INDEX
    Explanations

    ence

    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
    ence
    -3.08
    ENCE
    -2.66
    ance
    -2.47
    ences
    -2.22
    ANCE
    -2.13
    ENCES
    -2.08
    ances
    -1.88
    nce
    -1.71
    ANCES
    -1.58
    enced
    -1.56
    POSITIVE LOGITS
     Мексичка
    0.84
     MainAxisSize
    0.83
    
    0.82
    styleType
    0.81
     GenerationType
    0.79
    InitVars
    0.77
     كومونز
    0.76
    IntoConstraints
    0.74
    NgModule
    0.72
    rungsseite
    0.71
    Activations Density 0.327%

    No Known Activations