Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74037
    Prev
    Next
    INDEX
    Explanations

    X mark

    np_max-act-logits · 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
    setVerticalGroup
    -0.69
    makeConstraints
    -0.63
    OpenHelper
    -0.63
    ArgsConstructor
    -0.61
    landais
    -0.60
    Vorte
    -0.57
    Alike
    -0.57
    oredCriteria
    -0.54
    NgModule
    -0.54
    olge
    -0.54
    POSITIVE LOGITS
     X
    0.79
    X
    0.71
    ⓧ
    0.67
     x
    0.63
     Xo
    0.56
    x
    0.52
     cross
    0.51
    X
    0.51
    AddTagHelper
    0.50
     croix
    0.49
    Activations Density 0.000%

    No Known Activations