© 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. 1-CLT-HP
    7. 15609
    Prev
    Next
    INDEX
    Explanations

    Neuroscience/Biology

    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
    alt
    -0.47
    al
    -0.43
    aroa
    -0.42
    findpost
    -0.40
    le
    -0.39
    ia
    -0.39
    ias
    -0.38
    alty
    -0.38
     mec
    -0.37
    a
    -0.37
    POSITIVE LOGITS
    BufferException
    0.79
    adaptiveStyles
    0.75
    SequentialGroup
    0.73
    出版年
    0.73
    rungsseite
    0.72
    TintMode
    0.71
     يتيمه
    0.70
    WebVitals
    0.70
    LVANIA
    0.70
     ComVisible
    0.70
    Activations Density 0.172%

    No Known Activations