© 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. 92565
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    NavLink
    -0.40
    ⁢
    -0.39
    SNAP
    -0.39
     Sov
    -0.38
    <bos>
    -0.36
    DELETE
    -0.36
    らせて
    -0.36
    GET
    -0.36
    connexion
    -0.36
     émotion
    -0.35
    POSITIVE LOGITS
    CloseOperation
    0.90
    RegistryLite
    0.78
    DockStyle
    0.77
    ItemBackground
    0.77
    extAlignment
    0.77
     الدولى
    0.76
    ArrowToggle
    0.76
    +#+#
    0.73
     LoggerFactory
    0.71
    AnchorStyles
    0.68
    Activations Density 0.007%

    No Known Activations