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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3337
    Prev
    Next
    INDEX
    Explanations

    email

    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
     snippetHide
    -0.96
     arşivlendi
    -0.78
    Искәрмәләр
    -0.77
    HideFlags
    -0.76
     raiſ
    -0.76
     насељу
    -0.75
     defaultstate
    -0.73
     himſelf
    -0.73
    MigrationBuilder
    -0.73
     nakalista
    -0.73
    POSITIVE LOGITS
    Advertisement
    0.51
     -
    0.47
     A
    0.46
     
    0.44
     :
    0.44
     fair
    0.43
     Fair
    0.43
    grà
    0.43
    hythm
    0.43
    :
    0.43
    Activations Density 0.062%

    No Known Activations