© 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. 97459
    Prev
    Next
    INDEX
    Explanations

    CAD

    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
    DECREF
    -0.53
     validamos
    -0.46
     acci
    -0.44
    pstead
    -0.43
    expandindo
    -0.42
     Waray
    -0.42
    Източници
    -0.42
    stdc
    -0.42
    esez
    -0.41
     Chappell
    -0.41
    POSITIVE LOGITS
    TypedDataSet
    0.68
     AssemblyProduct
    0.63
    +:+
    0.63
     "..\..\..\
    0.62
     فريبيس
    0.62
    MigrationBuilder
    0.60
     يتيمه
    0.59
     BufferedImage
    0.58
    GEBURTSDATUM
    0.57
     Revit
    0.56
    Activations Density 0.001%

    No Known Activations