© 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. 336
    Prev
    Next
    INDEX
    Explanations

    factor

    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
    uisine
    -0.47
    Such
    -0.45
     Such
    -0.44
    nocześnie
    -0.44
     such
    -0.43
     Himo
    -0.42
    logan
    -0.41
    have
    -0.41
     bother
    -0.40
     Chwiliwch
    -0.40
    POSITIVE LOGITS
    PMailer
    0.70
    tinyos
    0.63
     in
    0.63
    InBackground
    0.62
    ImageContext
    0.61
    SequentialGroup
    0.57
     charges
    0.57
    Przypisy
    0.56
    TargetException
    0.56
     defStyle
    0.55
    Activations Density 0.032%

    No Known Activations