© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45688
    Prev
    Next
    INDEX
    Explanations

    Random text

    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
     Purcell
    -0.82
    AccessorTable
    -0.81
    AddTagHelper
    -0.69
    Дереккөздер
    -0.66
     defaultstate
    -0.62
    ագրություններ
    -0.60
    medriver
    -0.60
    uxxxx
    -0.60
     Antar
    -0.58
    animous
    -0.58
    POSITIVE LOGITS
    FieldBuilder
    0.52
    ervative
    0.49
     Sab
    0.46
     Group
    0.46
    嘧
    0.46
    qrstuvwxyz
    0.45
    //
    0.44
    logrus
    0.44
     Amp
    0.43
    ombang
    0.43
    Activations Density 0.019%

    No Known Activations