© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94406
    Prev
    Next
    INDEX
    Explanations

    incumbent

    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
    ollectionView
    -0.68
    artifactId
    -0.59
    fml
    -0.57
     StatelessWidget
    -0.56
    WriteBarrier
    -0.55
     Meksiku
    -0.54
    CIM
    -0.52
    stdc
    -0.51
    IntoConstraints
    -0.50
    !*\
    -0.49
    POSITIVE LOGITS
    rances
    0.69
     défa
    0.57
    rance
    0.54
    utives
    0.54
    ents
    0.50
    inos
    0.49
    umb
    0.49
    ChildScrollView
    0.47
    ency
    0.46
    Билгалдахарш
    0.45
    Activations Density 0.009%

    No Known Activations