© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3243
    Prev
    Next
    INDEX
    Explanations

    if/that

    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
     يتيمه
    -0.86
     ModelExpression
    -0.70
     متعلقه
    -0.68
    出版年
    -0.67
    DoubleQuotes
    -0.65
     having
    -0.59
     being
    -0.57
    RTDA
    -0.56
    ("")]
    -0.56
    これを
    -0.56
    POSITIVE LOGITS
     the
    0.79
    (;;)
    0.66
    certain
    0.62
     certain
    0.60
     they
    0.60
    SupportActionBar
    0.60
    most
    0.56
     some
    0.56
    liest
    0.53
     most
    0.51
    Activations Density 0.003%

    No Known Activations