© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97489
    Prev
    Next
    INDEX
    Explanations

    .

    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
     We
    -0.75
     But
    -0.73
     Codes
    -0.71
     And
    -0.71
     Ok
    -0.71
     Let
    -0.70
     Code
    -0.70
     Link
    -0.70
    __(/*!
    -0.69
     Click
    -0.69
    POSITIVE LOGITS
    A
    0.59
    "
    0.55
    It
    0.54
    He
    0.52
    In
    0.52
    I
    0.50
    As
    0.50
    B
    0.49
    If
    0.48
    So
    0.48
    Activations Density 0.014%

    No Known Activations