© 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. 5025
    Prev
    Next
    INDEX
    Explanations

    should

    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
     surla
    -0.66
    abestanden
    -0.61
     gynhyrchwyd
    -0.61
     Tipp
    -0.57
    évaluateur
    -0.57
    ichè
    -0.54
    ட்டி
    -0.54
    ynie
    -0.54
    names
    -0.54
    ίνη
    -0.54
    POSITIVE LOGITS
     lead
    0.68
    ]--;
    0.64
     decide
    0.60
     own
    0.58
    }\]
    0.56
     participate
    0.56
    #
    0.56
     read
    0.56
     sign
    0.53
    ]$}
    0.53
    Activations Density 0.009%

    No Known Activations