© 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. 5-CLT-HP
    7. 5458
    Prev
    Next
    INDEX
    Explanations

    batch

    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
     BoxFit
    -0.75
     myſelf
    -0.75
     otomatig
    -0.75
    LookAnd
    -0.74
    ollectionView
    -0.69
     المعيارى
    -0.68
    AsUp
    -0.67
     وتسجيلات
    -0.67
    makeConstraints
    -0.66
    UnusedPrivate
    -0.66
    POSITIVE LOGITS
     and
    0.80
     depending
    0.66
    ,
    0.61
    depending
    0.58
     but
    0.55
     person
    0.50
    جغرافيا
    0.46
    .
    0.45
     if
    0.44
     ale
    0.44
    Activations Density 0.003%

    No Known Activations