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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11134
    Prev
    Next
    INDEX
    Explanations

    method

    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
    mybatisplus
    -0.77
     Bioaccumulative
    -0.77
    thâu
    -0.71
    Bioaccumulative
    -0.69
    MethodManager
    -0.69
     JpaRepository
    -0.69
    enoord
    -0.68
    IComponent
    -0.65
     nawr
    -0.63
     ẞ
    -0.62
    POSITIVE LOGITS
     to
    0.69
    <bos>
    0.49
     of
    0.48
     out
    0.46
     para
    0.45
    ضى
    0.44
     concern
    0.44
     behind
    0.42
     where
    0.41
     in
    0.40
    Activations Density 0.009%

    No Known Activations