© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44145
    Prev
    Next
    INDEX
    Explanations

    fine details and granular materials

    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
     fin
    -1.13
    Fin
    -1.02
     Fin
    -1.01
    fin
    -1.00
    FIN
    -0.96
     finest
    -0.95
     FIN
    -0.90
     Finest
    -0.84
     finos
    -0.72
     finely
    -0.71
    POSITIVE LOGITS
    ագրություններ
    1.01
     تانيه
    0.88
    AddTagHelper
    0.81
     مرئيه
    0.77
    tagHelperRunner
    0.73
    kmäler
    0.73
     متعلقه
    0.72
    EndInit
    0.71
    theless
    0.67
    TagMode
    0.66
    Activations Density 0.812%

    No Known Activations