© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2503
    Prev
    Next
    INDEX
    Explanations

    show

    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
    CloseOperation
    -0.76
    +#+#
    -0.74
    EDEFAULT
    -0.73
    //});
    -0.73
    WithIOException
    -0.69
    SequentialGroup
    -0.68
    IntoConstraints
    -0.67
    embatan
    -0.64
    __":
    -0.64
     ExecuteAsync
    -0.63
    POSITIVE LOGITS
     us
    0.52
     Cina
    0.46
     her
    0.45
     enjoyed
    0.45
    off
    0.45
     control
    0.43
     follow
    0.43
     Follow
    0.42
    Follow
    0.42
     to
    0.41
    Activations Density 0.006%

    No Known Activations