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. 74202
    Prev
    Next
    INDEX
    Explanations

    code/markup

    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
    sizeCache
    -0.76
    MessageOf
    -0.74
    EDEFAULT
    -0.74
    uxxxx
    -0.73
    msgTypes
    -0.72
     SwitchCompat
    -0.71
    Panamoan
    -0.69
     initComponents
    -0.67
    UIControlState
    -0.66
    примеча
    -0.66
    POSITIVE LOGITS
     duros
    0.44
    lays
    0.38
    ioutil
    0.37
    رفت
    0.37
     fVar
    0.36
     bu
    0.35
    stellung
    0.35
     veze
    0.35
    PY
    0.35
    aries
    0.35
    Activations Density 0.002%

    No Known Activations