© 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. 5-CLT-HP
    7. 96091
    Prev
    Next
    INDEX
    Explanations

    0

    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
    heira
    -0.56
     Houſe
    -0.54
     Eſ
    -0.50
    pædia
    -0.49
    eſt
    -0.49
    pip
    -0.49
    pano
    -0.49
    $.
    -0.48
    enumi
    -0.48
     ―――――
    -0.47
    POSITIVE LOGITS
     onCreateView
    0.55
     createState
    0.54
     Réponses
    0.52
    Lähteet
    0.51
     aceptas
    0.51
     (
    0.50
    ⓧ
    0.48
     consultato
    0.47
    رشف
    0.47
     Agreed
    0.45
    Activations Density 0.026%

    No Known Activations