© 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. 5-CLT-HP
    4. 1135
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Another
    -0.62
     Another
    -0.59
    another
    -0.57
     Himself
    -0.57
     Rima
    -0.53
     another
    -0.52
    aby
    -0.52
     Idem
    -0.52
    ungguhnya
    -0.49
     yet
    -0.49
    POSITIVE LOGITS
    PUBLISHED
    0.56
    ########.
    0.55
    antMatchers
    0.55
    GeoNames
    0.54
    findpost
    0.54
     existing
    0.53
     surla
    0.53
     saites
    0.53
     Lightboxes
    0.53
     mijne
    0.52
    Activations Density 0.005%

    No Known Activations