© 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. 796
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
    findpost
    -0.55
    nių
    -0.49
    visející
    -0.44
     Houſe
    -0.42
    splitlines
    -0.42
    rmdir
    -0.42
    vų
    -0.41
    rstrip
    -0.40
    lepší
    -0.40
    putstr
    -0.40
    POSITIVE LOGITS
    in
    0.81
    dis
    0.80
    all
    0.77
    this
    0.77
    mis
    0.76
    the
    0.76
    as
    0.76
    for
    0.75
    long
    0.75
    one
    0.75
    Activations Density 0.182%

    No Known Activations