© 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. 20-CLT-HP
    7. 77157
    Prev
    Next
    INDEX
    Explanations

    Mixed topics

    np_max-act-logits · 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
     InputDecoration
    -0.89
     विश्वसनीयता
    -0.84
     économiques
    -0.78
    UnsafeEnabled
    -0.77
    elemField
    -0.74
    GEBURTSDATUM
    -0.74
    MetaObject
    -0.73
     noires
    -0.72
     financières
    -0.72
    expandindo
    -0.71
    POSITIVE LOGITS
     Arhi
    0.39
     bugs
    0.39
     good
    0.38
    роде
    0.36
    ('
    0.35
     bug
    0.35
    Bug
    0.35
    一口
    0.33
     short
    0.33
    ("
    0.32
    Activations Density 0.000%

    No Known Activations