Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73888
    Prev
    Next
    INDEX
    Explanations

    Code, foreign language and titles

    np_max-act-logits · 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
    ⓧ
    -0.74
    Geplaatst
    -0.66
    IntoConstraints
    -0.64
    mappedBy
    -0.59
     full
    -0.59
    IGraphics
    -0.58
    Personendaten
    -0.57
     vollen
    -0.57
     initWithFrame
    -0.56
    abestanden
    -0.54
    POSITIVE LOGITS
     Sour
    0.55
    thâu
    0.54
     []:
    0.54
     AspNetCore
    0.53
     Poc
    0.51
    gebob
    0.51
    \{\\
    0.50
     jep
    0.50
    ่ง
    0.49
     Sú
    0.48
    Activations Density 0.005%

    No Known Activations