© 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. 1-CLT-HP
    7. 10395
    Prev
    Next
    INDEX
    Explanations

    positive

    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
    basicConfig
    -0.68
    CppMethod
    -0.47
    ViewFeatures
    -0.47
     SafeMath
    -0.46
    WebMethod
    -0.46
    positive
    -0.45
    ]").
    -0.44
    ground
    -0.44
    ξης
    -0.44
     positive
    -0.43
    POSITIVE LOGITS
    SharedCtor
    0.67
    SBATCH
    0.63
    AnchorTagHelper
    0.63
     IndexPath
    0.57
    SPATH
    0.56
    Cubit
    0.55
    脚注の使い方
    0.54
     HMS
    0.54
    ORA
    0.54
    Ārējās
    0.54
    Activations Density 0.031%

    No Known Activations