© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77709
    Prev
    Next
    INDEX
    Explanations

    code and copyright

    np_max-act-logits · 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
    DIPSETTING
    -0.74
    RectangleBorder
    -0.70
    SourceChecksum
    -0.69
    AddTagHelper
    -0.68
    SBATCH
    -0.68
     invokingState
    -0.67
    WriteTagHelper
    -0.65
    OfWork
    -0.65
     getItemCount
    -0.63
    UrlResolution
    -0.63
    POSITIVE LOGITS
    abetes
    0.45
    quelize
    0.39
    risti
    0.38
    stok
    0.37
    fte
    0.37
    ########.
    0.37
    Es
    0.36
    ыргыз
    0.35
    Ed
    0.35
    velt
    0.35
    Activations Density 0.001%

    No Known Activations