© 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. 96049
    Prev
    Next
    INDEX
    Explanations

    copyright names

    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
    ollectionView
    -0.72
    AccessorTable
    -0.71
     TestBed
    -0.70
     ligiloj
    -0.67
     Vikipedi
    -0.65
    +#+#
    -0.64
    Personensuche
    -0.60
    Spoljašnje
    -0.60
    ScopeManager
    -0.58
     الحره
    -0.57
    POSITIVE LOGITS
     supposed
    0.59
    ürk
    0.56
    SizeMode
    0.54
     alleged
    0.51
    raisemb
    0.47
    midler
    0.47
     peran
    0.45
    supposed
    0.45
    tifkan
    0.43
     posibles
    0.43
    Activations Density 0.014%

    No Known Activations