© 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. 4-CLT-HP
    7. 3341
    Prev
    Next
    INDEX
    Explanations

    with

    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
    same
    -0.58
    حوالہ
    -0.56
    equalTo
    -0.54
    CPtr
    -0.53
    +#+#
    -0.51
     Similarly
    -0.51
    makeConstraints
    -0.48
    being
    -0.47
    DOCTYPE
    -0.47
     territoire
    -0.47
    POSITIVE LOGITS
     GenerationType
    0.69
    RegressionTest
    0.58
     sufficient
    0.57
     uitges
    0.57
     typelib
    0.54
    jstor
    0.54
     adequate
    0.54
     a
    0.54
    AsUp
    0.54
     betweenstory
    0.53
    Activations Density 0.015%

    No Known Activations