© 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. 0-CLT-HP
    7. 94293
    Prev
    Next
    INDEX
    Explanations

    proposals

    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
     we
    -0.56
     understand
    -0.48
    :
    -0.46
     check
    -0.44
     us
    -0.43
     the
    -0.43
     change
    -0.42
     action
    -0.41
     nous
    -0.40
    pyplot
    -0.40
    POSITIVE LOGITS
     المعيارى
    1.06
    NameInMap
    1.01
    WithIOException
    1.01
     Efq
    0.94
    @[+][
    0.93
    InjectAttribute
    0.93
     StringTokenizer
    0.88
     EconPapers
    0.88
    évaluateur
    0.85
    ThroughAttribute
    0.85
    Activations Density 0.103%

    No Known Activations