© 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. 4-CLT-HP
    7. 864
    Prev
    Next
    INDEX
    Explanations

    Creation/Requirement

    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
    <bos>
    -0.81
    捜査
    -0.42
    uri
    -0.40
    bu
    -0.40
    ونم
    -0.40
    anlage
    -0.40
    R
    -0.39
     flesta
    -0.39
    wür
    -0.39
     and
    -0.38
    POSITIVE LOGITS
     ModelExpression
    0.75
     >=",
    0.73
    setVerticalGroup
    0.73
    NUMX
    0.70
    TagMode
    0.69
    AnchorStyles
    0.68
     firſt
    0.67
     myſelf
    0.67
     beſt
    0.67
    TestingModule
    0.67
    Activations Density 0.002%

    No Known Activations