© 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. 72138
    Prev
    Next
    INDEX
    Explanations

    Code, data, metadata

    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
    expandindo
    -0.98
     itſelf
    -0.87
     raiſ
    -0.84
    homonymie
    -0.82
    Tembelea
    -0.80
    Tazama
    -0.78
     Theſe
    -0.78
    windowFixed
    -0.77
    ſelves
    -0.76
    AsUp
    -0.76
    POSITIVE LOGITS
     were
    0.87
    <eos>
    0.61
     chose
    0.59
     are
    0.57
     did
    0.56
     was
    0.55
     fell
    0.54
     took
    0.54
     to
    0.52
    Personendaten
    0.51
    Activations Density 0.001%

    No Known Activations