© 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. 0-CLT-HP
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    chemical and biological processes

    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
    ever
    -0.58
    rungsseite
    -0.56
    migrationBuilder
    -0.54
    avigation
    -0.52
    rolid
    -0.52
     OMITBAD
    -0.52
    ectomy
    -0.51
    epiece
    -0.51
    commodation
    -0.49
     ujednoznacz
    -0.49
    POSITIVE LOGITS
    s
    1.52
    ی
    0.89
    ness
    0.87
    sic
    0.75
    ים
    0.71
    nesses
    0.69
    NESS
    0.68
    sab
    0.67
    ся
    0.66
    schen
    0.65
    Activations Density 1.275%

    No Known Activations