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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3706
    Prev
    Next
    INDEX
    Explanations

    Copyright/code

    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
     gyhoeddwyd
    -0.72
    onomía
    -0.69
    mybatisplus
    -0.68
    PHeader
    -0.65
    PreferredItem
    -0.65
     lèvres
    -0.63
    ngrx
    -0.60
    Климат
    -0.59
     dieux
    -0.59
    :✨
    -0.59
    POSITIVE LOGITS
    UVWXYZ
    0.46
     ExecuteAsync
    0.41
     AttributeSet
    0.40
    TextEditing
    0.40
    VersionUID
    0.40
    Personensuche
    0.40
    APOLIS
    0.40
     times
    0.40
    Executives
    0.39
     kaarangay
    0.39
    Activations Density 0.000%

    No Known Activations