© 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. 43015
    Prev
    Next
    INDEX
    Explanations

    yes

    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
    yes
    -1.49
     yes
    -0.99
    YES
    -0.86
    rungsseite
    -0.84
    Yes
    -0.82
    انجليز
    -0.73
     Yes
    -0.73
    endphp
    -0.73
     فريبيس
    -0.71
    üyada
    -0.70
    POSITIVE LOGITS
     Remaining
    0.59
    Herzliche
    0.52
     őket
    0.51
     descubrimiento
    0.50
    yntaxException
    0.49
     rând
    0.49
    Remaining
    0.47
    heet
    0.46
     noastre
    0.46
     stesso
    0.45
    Activations Density 0.220%

    No Known Activations