© 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. 42306
    Prev
    Next
    INDEX
    Explanations

    Services provided

    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
     happen
    -1.11
     happened
    -1.05
     served
    -0.90
     happens
    -0.89
     dates
    -0.87
    happen
    -0.81
    happened
    -0.81
     happening
    -0.79
     Happened
    -0.73
     Served
    -0.72
    POSITIVE LOGITS
     Paglinawan
    0.61
    elemField
    0.59
     المعيارى
    0.58
    SerializedSize
    0.57
    יף
    0.56
    ɕ
    0.54
    Géographie
    0.53
    стьян
    0.53
    spiller
    0.52
     виправивши
    0.52
    Activations Density 0.042%

    No Known Activations