© 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. 4-CLT-HP
    4. 3304
    Prev
    Next
    INDEX
    Explanations

    lists and sequences

    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
     anything
    -0.47
     any
    -0.47
     ulter
    -0.44
     conos
    -0.44
    によ
    -0.44
     nume
    -0.42
     mentales
    -0.41
     altre
    -0.41
     st
    -0.40
     meg
    -0.39
    POSITIVE LOGITS
     дописавши
    0.71
     turning
    0.69
    prefixer
    0.68
    RTLD
    0.66
    fromnode
    0.66
    adaptiveStyles
    0.63
     aikaa
    0.63
    AddTagHelper
    0.61
     الرياضيه
    0.61
    bParam
    0.60
    Activations Density 0.002%

    No Known Activations