© 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. 0-CLT-HP
    7. 42778
    Prev
    Next
    INDEX
    Explanations

    Plus

    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
     Plus
    -0.82
    Plus
    -0.62
    ly
    -0.57
    enumi
    -0.54
    lex
    -0.49
    发表于
    -0.49
    Hence
    -0.49
    s
    -0.48
    sil
    -0.47
     customize
    -0.47
    POSITIVE LOGITS
    RAINE
    0.67
     sureties
    0.66
     protoimpl
    0.65
    rrggbb
    0.64
    Parcelize
    0.62
     Baillargeon
    0.61
    ModelSerializer
    0.59
    msgSender
    0.59
    transQ
    0.58
    DeleteBehavior
    0.58
    Activations Density 1.656%

    No Known Activations