© 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. 12299
    Prev
    Next
    INDEX
    Explanations

    titles and headings

    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
     betweenstory
    -0.69
     beginnetje
    -0.60
    ConstraintMaker
    -0.57
    EndProject
    -0.56
     CreateTagHelper
    -0.55
     Protección
    -0.55
    title
    -0.54
     nahilalakip
    -0.54
    chin
    -0.53
    IRMED
    -0.53
    POSITIVE LOGITS
    Hentet
    0.58
    Дереккөздер
    0.52
     antaranya
    0.52
     mergeFrom
    0.52
    antaranya
    0.48
    ItemBackground
    0.47
    intahan
    0.47
    ogaster
    0.46
    StartTag
    0.44
    ltä
    0.44
    Activations Density 0.159%

    No Known Activations