© 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. 1-CLT-HP
    7. 12337
    Prev
    Next
    INDEX
    Explanations

    onic

    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
    saraba
    -0.65
    MigrationBuilder
    -0.64
     defaultstate
    -0.57
    Pragma
    -0.55
    lardır
    -0.53
    RouterModule
    -0.52
     cerrada
    -0.51
    readystatechange
    -0.49
    غيرة
    -0.49
     amounts
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.76
    enumi
    0.56
    tagHelperRunner
    0.53
    deo
    0.52
    Legături
    0.50
     متعلقه
    0.48
    utivo
    0.48
    complexContent
    0.48
    Deus
    0.46
    IUrlHelper
    0.46
    Activations Density 0.014%

    No Known Activations