© 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. 5-CLT-HP
    7. 97239
    Prev
    Next
    INDEX
    Explanations

    risk

    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
    ✨:
    -0.59
     كمان
    -0.56
    ]!='
    -0.55
    ]=="
    -0.52
     tartalomajánló
    -0.52
    []=$
    -0.50
     auroit
    -0.49
     են
    -0.48
    yship
    -0.48
    loyment
    -0.48
    POSITIVE LOGITS
     المعيارى
    0.85
    ArgumentParser
    0.79
    ImageContext
    0.71
     about
    0.69
     in
    0.65
    HtmlAttribute
    0.59
     JpaRepository
    0.59
    VideoCapture
    0.57
     involved
    0.57
    about
    0.57
    Activations Density 0.000%

    No Known Activations