© 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. 1-CLT-HP
    7. 15537
    Prev
    Next
    INDEX
    Explanations

    natural

    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
     Paglinawan
    -0.64
    leto
    -0.51
    }}_{
    -0.51
    face
    -0.46
     spread
    -0.46
    hadapi
    -0.45
    }}_{\
    -0.44
    >(_
    -0.44
     set
    -0.43
    lète
    -0.43
    POSITIVE LOGITS
    Tikang
    0.65
     mitz
    0.64
    ised
    0.63
    MarshalTo
    0.57
     noqa
    0.57
     BoxFit
    0.55
    ized
    0.55
     oike
    0.54
    Rhestr
    0.54
     rights
    0.54
    Activations Density 0.035%

    No Known Activations