© 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. 4181
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    rhs
    -0.48
    IKI
    -0.45
    d
    -0.45
    osz
    -0.44
    ・
    -0.44
    foot
    -0.44
    Ar
    -0.44
    mathit
    -0.44
     mực
    -0.44
    arlı
    -0.44
    POSITIVE LOGITS
    帖最后由
    0.77
    IsContent
    0.69
    MLLoader
    0.66
    CloseOperation
    0.65
    SharedDtor
    0.64
     CreateTagHelper
    0.64
    endpush
    0.63
     ExecuteAsync
    0.61
     >=",
    0.60
     linkovi
    0.59
    Activations Density 0.003%

    No Known Activations