© 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. 4-CLT-HP
    7. 77
    Prev
    Next
    INDEX
    Explanations

    Wikipedia articles

    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
    expandindo
    -0.80
    IVEREF
    -0.68
    #+#
    -0.67
    +#+#
    -0.66
     collectons
    -0.65
    AnchorStyles
    -0.64
    Buildable
    -0.64
    MIDDLEWARE
    -0.61
    Personensuche
    -0.61
    UnusedPrivate
    -0.61
    POSITIVE LOGITS
     up
    0.54
    ExtendWith
    0.49
    ROM
    0.46
    CRI
    0.44
     تر
    0.44
    nement
    0.44
     down
    0.44
    ConstraintMaker
    0.43
     before
    0.43
    DrawerToggle
    0.43
    Activations Density 0.005%

    No Known Activations