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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74611
    Prev
    Next
    INDEX
    Explanations

    Code and formulas

    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
    saraba
    -0.65
    //
    -0.64
    AddressBook
    -0.62
     AttributeSet
    -0.62
    BASEPATH
    -0.61
    featureID
    -0.60
    yntaxException
    -0.59
    höhung
    -0.57
    تقاوى
    -0.56
    HomeAsUpEnabled
    -0.56
    POSITIVE LOGITS
    醐
    0.49
    Aiheesta
    0.49
    self
    0.47
     talaga
    0.47
    Real
    0.47
    первых
    0.45
    ioutil
    0.43
    real
    0.42
    ándola
    0.42
     Gleaner
    0.42
    Activations Density 0.007%

    No Known Activations