© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1147
    Prev
    Next
    INDEX
    Explanations

    into

    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
    цездатний
    -0.65
     materna
    -0.64
    InjectAttribute
    -0.58
    ParallelGroup
    -0.56
     يتيمه
    -0.52
     Reinhold
    -0.51
     Normdatei
    -0.50
    الحياه
    -0.49
    migrationBuilder
    -0.48
     suggestions
    -0.48
    POSITIVE LOGITS
    rawDesc
    0.64
    httphttps
    0.61
    HomeAsUpEnabled
    0.57
    ficas
    0.49
    ivasan
    0.49
    ibatis
    0.47
    opend
    0.47
    @[+][
    0.47
     cliquant
    0.46
    palen
    0.46
    Activations Density 0.005%

    No Known Activations