© 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. 1-CLT-HP
    7. 10964
    Prev
    Next
    INDEX
    Explanations

    Makefile

    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
     itſelf
    -1.01
     Roskov
    -0.96
     myſelf
    -0.93
     ―――――
    -0.91
     Reſ
    -0.85
    ſelves
    -0.78
     ſtate
    -0.78
    ſelf
    -0.78
    StoryboardSegue
    -0.78
     Anſ
    -0.77
    POSITIVE LOGITS
    er
    0.57
    ek
    0.49
    <eos>
    0.48
    in
    0.47
     van
    0.46
    es
    0.46
     to
    0.46
    a
    0.45
    ica
    0.44
    om
    0.44
    Activations Density 0.016%

    No Known Activations