© 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. 94310
    Prev
    Next
    INDEX
    Explanations

    places and conflicts

    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
     molecules
    -1.03
    hips
    -0.82
     molecule
    -0.82
    ards
    -0.78
    molecules
    -0.63
     col
    -0.63
     Molecules
    -0.60
    col
    -0.59
     attempt
    -0.59
     molé
    -0.59
    POSITIVE LOGITS
    +#+#
    0.77
     AssemblyTitle
    0.68
     FetchType
    0.65
    endphp
    0.63
     IndexPath
    0.63
     initComponents
    0.58
    ValueStyle
    0.57
     itſelf
    0.56
     NavController
    0.55
     Grecs
    0.55
    Activations Density 0.275%

    No Known Activations