© 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. 460
    Prev
    Next
    INDEX
    Explanations

    tile

    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
    InjectAttribute
    -0.58
    TypedDataSet
    -0.57
     مرئيه
    -0.54
     gynhyrchwyd
    -0.54
    writerow
    -0.53
    PageRoute
    -0.52
    +#+#
    -0.52
    adaptiveStyles
    -0.50
    GEBURTSDATUM
    -0.50
    Personendaten
    -0.49
    POSITIVE LOGITS
     itſelf
    0.77
     iſt
    0.73
    ſelves
    0.73
     purpoſe
    0.71
     sterilization
    0.71
     Monfieur
    0.69
     $_"
    0.67
     Houſe
    0.66
    ſelf
    0.65
    ^(@)
    0.65
    Activations Density 0.034%

    No Known Activations