© 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. 993
    Prev
    Next
    INDEX
    Explanations

    the

    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
    jsonwebtoken
    -0.60
     متحده
    -0.58
    ellee
    -0.55
    veral
    -0.53
    ruptedException
    -0.51
    acherous
    -0.50
     snippetHide
    -0.50
    wyl
    -0.49
    ToProps
    -0.49
    astéroïdes
    -0.48
    POSITIVE LOGITS
    WithIOException
    0.71
     primary
    0.70
     principaux
    0.66
     principais
    0.64
     pagrind
    0.63
     haupts
    0.62
     main
    0.62
    primary
    0.61
     principali
    0.59
     základ
    0.58
    Activations Density 0.005%

    No Known Activations