© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91609
    Prev
    Next
    INDEX
    Explanations

    request

    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
    yntaxException
    -0.59
     vuitton
    -0.57
    Request
    -0.52
    partements
    -0.51
     adelante
    -0.51
    ParallelGroup
    -0.50
    Naissance
    -0.49
    orneys
    -0.49
    scribers
    -0.49
    المناصب
    -0.48
    POSITIVE LOGITS
    expandindo
    0.61
    IntoConstraints
    0.58
    קישורים
    0.56
    شوف
    0.53
    nonatomic
    0.52
     tartalomajánló
    0.50
     Pristup
    0.49
    RenderAtEndOf
    0.49
    原始内容存档于
    0.49
     a
    0.49
    Activations Density 0.006%

    No Known Activations