© 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. 20-CLT-HP
    7. 71970
    Prev
    Next
    INDEX
    Explanations

    Policy and services

    np_max-act-logits · 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
    NOPQRST
    -0.73
    parsedMessage
    -0.62
    Personendaten
    -0.53
    CloseOperation
    -0.53
    NUMX
    -0.51
    }))
    -0.51
    toThrow
    -0.50
    <?>>
    -0.49
    ^*)
    -0.49
    Traceback
    -0.48
    POSITIVE LOGITS
     Instruments
    0.56
     instruments
    0.56
     axes
    0.53
    pole
    0.52
     Operators
    0.52
     Axes
    0.50
     HORN
    0.50
     Operator
    0.49
     pote
    0.49
     Actions
    0.49
    Activations Density 0.000%

    No Known Activations