© 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. 91468
    Prev
    Next
    INDEX
    Explanations

    of

    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
     estekak
    -0.81
    Tikang
    -0.75
    ArgsConstructor
    -0.75
    UnusedPrivate
    -0.75
    httphttps
    -0.69
     autorytatywna
    -0.69
     MonoBehaviour
    -0.69
    TagMode
    -0.68
    Shaders
    -0.65
    ніципа
    -0.65
    POSITIVE LOGITS
     what
    0.78
     my
    0.64
     last
    0.63
     our
    0.56
     What
    0.53
     WHAT
    0.47
     one
    0.46
    what
    0.45
     nuestro
    0.43
     ciò
    0.42
    Activations Density 0.001%

    No Known Activations