© 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. 0-CLT-HP
    7. 97760
    Prev
    Next
    INDEX
    Explanations

    correlates

    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
     Signalez
    -0.72
     Englishmen
    -0.69
     '\\;'
    -0.66
     TeV
    -0.66
    s
    -0.66
     Sacrament
    -0.65
     sacrament
    -0.65
     Shakspeare
    -0.65
     ويكيميديا
    -0.65
    épar
    -0.65
    POSITIVE LOGITS
    UserScript
    0.50
    ufs
    0.48
    übers
    0.48
    Gambas
    0.48
     far
    0.47
     cui
    0.47
     couple
    0.47
     Gul
    0.47
    ul
    0.46
    ъ
    0.45
    Activations Density 0.135%

    No Known Activations