© 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. 5-CLT-HP
    7. 4547
    Prev
    Next
    INDEX
    Explanations

    duration

    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
     linkovi
    -0.94
    IntoConstraints
    -0.89
    GEBURTSDATUM
    -0.87
     الحره
    -0.85
    StoryboardSegue
    -0.84
    <bos>
    -0.78
    aarrggbb
    -0.75
     ProtoMessage
    -0.73
    AndEndTag
    -0.72
     <=",
    -0.70
    POSITIVE LOGITS
     now
    0.69
     désormais
    0.49
     теперь
    0.42
     dalamnya
    0.41
    ẓ
    0.40
     Betracht
    0.40
    gg
    0.40
     ?>">
    0.40
     maintenant
    0.39
     aimé
    0.39
    Activations Density 0.008%

    No Known Activations