© 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. 0-CLT-HP
    7. 43414
    Prev
    Next
    INDEX
    Explanations

    Technical/varied topics

    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
     Jefus
    -0.91
     ſeveral
    -0.87
     Majefty
    -0.86
     Anſ
    -0.84
     pleaſure
    -0.82
     purpoſe
    -0.82
     poffible
    -0.82
     Chriftian
    -0.80
     Efq
    -0.80
     Eſ
    -0.79
    POSITIVE LOGITS
    <bos>
    0.65
     فريبيس
    0.60
     beginnetje
    0.57
     />);
    0.54
    __":
    0.52
    <eos>
    0.50
     مشين
    0.49
     Réponses
    0.47
    endphp
    0.47
    __":
    0.45
    Activations Density 0.077%

    No Known Activations