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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74560
    Prev
    Next
    INDEX
    Explanations

    After

    np_max-act-logits · 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
    RenderAtEndOf
    -0.71
    Slf
    -0.68
    Clik
    -0.66
    RunWith
    -0.64
    GTCX
    -0.61
     تكبرها
    -0.59
    Medico
    -0.58
     doInBackground
    -0.57
    GraphicsUnit
    -0.56
    DockStyle
    -0.55
    POSITIVE LOGITS
     a
    0.52
    Eksterne
    0.51
    MigrationBuilder
    0.48
    contentLoaded
    0.46
    nami
    0.46
     }{@
    0.45
    blut
    0.41
     treated
    0.41
     fras
    0.39
    hian
    0.39
    Activations Density 0.007%

    No Known Activations