© 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. 97340
    Prev
    Next
    INDEX
    Explanations

    S

    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
    DockStyle
    -0.97
    +#+#
    -0.95
    AnchorStyles
    -0.94
    LookAnd
    -0.94
    脚注の使い方
    -0.90
     typelib
    -0.89
     CreateTagHelper
    -0.89
     BoxFit
    -0.85
    SequentialGroup
    -0.83
    aarrggbb
    -0.81
    POSITIVE LOGITS
    약
    0.52
    etate
    0.48
     faith
    0.45
     орден
    0.45
    gle
    0.43
     ";
    0.40
     Faith
    0.39
     sect
    0.39
    simo
    0.38
    bbe
    0.38
    Activations Density 0.005%

    No Known Activations