© 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. 98060
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    ./
    -0.47
    InstanceState
    -0.46
    /
    -0.45
    ButterKnife
    -0.43
    .
    -0.42
    maj
    -0.41
    jectures
    -0.39
    ..\..\
    -0.39
    oka
    -0.38
     Seidel
    -0.38
    POSITIVE LOGITS
    ThroughAttribute
    0.74
    PreferredItem
    0.72
    brainly
    0.68
     '\\;'
    0.66
     betweenstory
    0.66
    ArrowToggle
    0.65
    RenderAtEndOf
    0.64
    liesslich
    0.63
    DockStyle
    0.62
    ']")
    0.61
    Activations Density 0.026%

    No Known Activations