© 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. 14198
    Prev
    Next
    INDEX
    Explanations

    exact

    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
     وتسجيلات
    -0.73
    URLException
    -0.69
     exactly
    -0.57
    CloseOperation
    -0.57
     precisely
    -0.56
    GEBURTSDATUM
    -0.56
    NewLabel
    -0.55
    RectangleBorder
    -0.54
    ToAction
    -0.51
     exactement
    -0.51
    POSITIVE LOGITS
     same
    0.78
     reason
    0.76
     way
    0.75
     moment
    0.67
     right
    0.65
     amount
    0.60
    GenerationType
    0.60
     slightest
    0.59
     reasons
    0.58
     reafon
    0.57
    Activations Density 0.018%

    No Known Activations