© 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. 0-CLT-HP
    7. 40706
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    TypedDataSet
    -0.63
     ControllerBase
    -0.57
    ButterKnife
    -0.56
     collè
    -0.55
    BeginInit
    -0.54
    herself
    -0.54
    unyai
    -0.53
    SequentialGroup
    -0.52
    aarrggbb
    -0.52
    AnchorStyles
    -0.52
    POSITIVE LOGITS
    <bos>
    1.38
    ,
    0.99
    Vidite
    0.65
    s
    0.55
     the
    0.49
    And
    0.48
    When
    0.47
    MeasureSpec
    0.47
    ，
    0.46
    พ
    0.46
    Activations Density 0.041%

    No Known Activations