© 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. 98019
    Prev
    Next
    INDEX
    Explanations

    effect

    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
    Huge
    -0.49
    そもそも
    -0.43
    hab
    -0.41
     enormous
    -0.40
     unprecedented
    -0.40
     przecież
    -0.40
     countless
    -0.40
     vieta
    -0.39
     ведь
    -0.38
    >>
    -0.38
    POSITIVE LOGITS
    __":
    1.22
    __':
    1.18
    awtextra
    1.13
    StructEnd
    1.00
    addContainerGap
    0.93
    __":
    0.92
     surla
    0.90
    parsedMessage
    0.89
    __':
    0.86
    esModule
    0.86
    Activations Density 0.074%

    No Known Activations