© 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. 97622
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    buttonBar
    -0.66
    styleUrls
    -0.64
    исленность
    -0.60
    gery
    -0.59
    UrlResolution
    -0.58
    참고
    -0.57
    ніципалі
    -0.56
    XmlAccessorType
    -0.56
    skjaer
    -0.56
    MigrationBuilder
    -0.56
    POSITIVE LOGITS
     nahilalakip
    0.53
    <bos>
    0.49
     holotype
    0.49
     precipitate
    0.46
     betweenstory
    0.46
    Composable
    0.46
     Nauk
    0.46
    colhead
    0.43
    brei
    0.43
    mstyle
    0.42
    Activations Density 0.005%

    No Known Activations