© 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. 45264
    Prev
    Next
    INDEX
    Explanations

    Pope

    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
     Cæsar
    -0.90
     pope
    -0.89
     Pope
    -0.86
     Romans
    -0.84
     romana
    -0.81
     Rome
    -0.79
    Pope
    -0.78
     römischen
    -0.73
    Rome
    -0.66
     romano
    -0.65
    POSITIVE LOGITS
     مرئيه
    0.70
    stdc
    0.63
    NgModule
    0.62
    coaster
    0.60
     שוליים
    0.58
    ="{{
    0.56
     AppComponent
    0.54
    createComponent
    0.54
    logrus
    0.54
    utrients
    0.53
    Activations Density 0.308%

    No Known Activations