© 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. 43969
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    adden
    -2.72
     Madden
    -0.85
     madden
    -0.77
     Roskov
    -0.61
     tfsi
    -0.60
    enterOuterAlt
    -0.59
    Added
    -0.57
     مواليد
    -0.56
    Add
    -0.56
    CascadeType
    -0.56
    POSITIVE LOGITS
    DoubleQuotes
    0.58
    itespace
    0.56
    \{\\
    0.49
    catholic
    0.49
    Cyfeiriadau
    0.47
    Bism
    0.47
     keskus
    0.47
     mahdollis
    0.46
     Pradesh
    0.45
    akteur
    0.45
    Activations Density 0.094%

    No Known Activations