© 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. 39806
    Prev
    Next
    INDEX
    Explanations

    therapy

    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
    AddTagHelper
    -0.85
    berdayakan
    -0.81
    IsMutable
    -0.75
     férfi
    -0.69
     traités
    -0.65
     ſtate
    -0.65
    ^(@)
    -0.64
    Rüyada
    -0.63
     poffe
    -0.63
     Monfieur
    -0.62
    POSITIVE LOGITS
     Cl
    0.51
     Cla
    0.50
     ujednoznacz
    0.48
     Branch
    0.48
    Externé
    0.48
    fatti
    0.47
     Nob
    0.47
    ubo
    0.46
    LEV
    0.45
     Cer
    0.45
    Activations Density 0.206%

    No Known Activations