© 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. 93186
    Prev
    Next
    INDEX
    Explanations

    Wikipedia excerpts

    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
    sidemargin
    -0.55
     SqlDbType
    -0.51
    DockStyle
    -0.46
    VersionUID
    -0.46
    mybatisplus
    -0.45
     Marquis
    -0.43
    zzleHttp
    -0.43
    AutoField
    -0.43
     Kamis
    -0.43
    dafx
    -0.42
    POSITIVE LOGITS
     pitié
    0.64
     Served
    0.63
    הערות
    0.59
     reposer
    0.56
     Available
    0.56
     zucca
    0.55
     Visited
    0.54
     simpto
    0.54
     charité
    0.54
     Feed
    0.53
    Activations Density 0.004%

    No Known Activations