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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 979
    Prev
    Next
    INDEX
    Explanations

    level

    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
     Roskov
    -0.50
    Hentet
    -0.49
    ALM
    -0.46
    ised
    -0.45
    odar
    -0.45
    theim
    -0.44
    SCO
    -0.42
     وتسجيلات
    -0.42
    voja
    -0.42
    cke
    -0.42
    POSITIVE LOGITS
    ReusableCell
    0.70
    RuleContext
    0.69
    #+#
    0.66
    ArrowToggle
    0.65
     "..\..\
    0.65
     "..\..\..\
    0.63
    ViewFeatures
    0.63
     ProtoMessage
    0.62
    manteau
    0.61
     blasphemy
    0.61
    Activations Density 0.060%

    No Known Activations