© 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. 0-CLT-HP
    7. 41427
    Prev
    Next
    INDEX
    Explanations

    exhibited

    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
    AxisAlignment
    -0.86
     ſever
    -0.82
     HasFactory
    -0.81
     ſen
    -0.80
     ſta
    -0.80
     Diſ
    -0.79
     houſe
    -0.78
     Anſ
    -0.77
     ſtate
    -0.77
     EconPapers
    -0.77
    POSITIVE LOGITS
     are
    0.62
     can
    0.55
     متعلقه
    0.49
    วะ
    0.46
    ,
    0.46
    stop
    0.45
    ed
    0.45
     A
    0.44
     would
    0.44
    '
    0.44
    Activations Density 1.631%

    No Known Activations