© 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. 0-CLT-HP
    7. 93095
    Prev
    Next
    INDEX
    Explanations

    What

    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
     enfans
    -0.93
    tvguidetime
    -0.89
     auffi
    -0.85
    #+#
    -0.83
    Hentet
    -0.82
    IntoConstraints
    -0.81
     Reſ
    -0.81
     itſelf
    -0.79
    jsonwebtoken
    -0.77
     myſelf
    -0.76
    POSITIVE LOGITS
     is
    1.27
    '
    1.16
    ’
    1.09
     was
    0.99
     are
    0.92
     do
    0.84
     would
    0.83
     does
    0.82
     will
    0.81
     did
    0.81
    Activations Density 0.054%

    No Known Activations