© 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. 4-CLT-HP
    7. 865
    Prev
    Next
    INDEX
    Explanations

    article "a"

    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
    <bos>
    -0.54
     deportivos
    -0.49
     klara
    -0.47
    ⓧ
    -0.46
     sports
    -0.46
     Sports
    -0.45
    cfm
    -0.43
    no
    -0.43
    eded
    -0.41
    ay
    -0.41
    POSITIVE LOGITS
    principalTable
    0.85
     المعيارى
    0.84
     CreateTagHelper
    0.80
     ddelweddau
    0.77
     الحره
    0.75
     виправивши
    0.74
     tartalomajánló
    0.71
    Jeografia
    0.68
     שוליים
    0.68
    parsedMessage
    0.67
    Activations Density 0.002%

    No Known Activations