© 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. 5-CLT-HP
    7. 5066
    Prev
    Next
    INDEX
    Explanations

    ana

    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
    IsMutable
    -0.55
    CloseOperation
    -0.51
     ―――――
    -0.51
     AVL
    -0.51
    RTLR
    -0.48
     Superhost
    -0.48
    ########.
    -0.47
     defStyle
    -0.47
     PCL
    -0.46
     FOB
    -0.46
    POSITIVE LOGITS
     Evangelio
    0.49
     procès
    0.48
     behand
    0.48
     çalışmalar
    0.48
    SourceChecksum
    0.46
     discursos
    0.46
     profeta
    0.46
     défense
    0.46
     egip
    0.45
    amssymb
    0.45
    Activations Density 0.003%

    No Known Activations