© 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. 97764
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and technical language

    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
     PW
    -0.61
    PW
    -0.59
     Carnegie
    -0.54
    CEP
    -0.53
     vocale
    -0.50
    y
    -0.46
     CW
    -0.46
    arpa
    -0.46
     antaranya
    -0.46
    olate
    -0.44
    POSITIVE LOGITS
    RegistryLite
    0.77
     HasFactory
    0.75
    InvalidProtocol
    0.74
    SourceChecksum
    0.70
     Eck
    0.65
     Macle
    0.64
    PMID
    0.63
    kloped
    0.63
    ueba
    0.62
    TagMode
    0.62
    Activations Density 0.122%

    No Known Activations