Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12590
    Prev
    Next
    INDEX
    Explanations

    therm-

    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
    Étienne
    -0.52
     RegExp
    -0.52
     IEnumerator
    -0.51
    numerusform
    -0.49
     invitations
    -0.48
     invites
    -0.47
     represent
    -0.47
     verify
    -0.47
     المعيارى
    -0.47
     escon
    -0.47
    POSITIVE LOGITS
     كومونز
    0.73
    MigrationBuilder
    0.64
    fjspx
    0.61
     ModelExpression
    0.58
    ContentAlignment
    0.57
     فريبيس
    0.57
    RegressionTest
    0.56
     transfieras
    0.56
     незавершена
    0.54
    دانشنامهٔ
    0.54
    Activations Density 0.006%

    No Known Activations