© 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. 94822
    Prev
    Next
    INDEX
    Explanations

    robust

    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
     typical
    -0.88
     exceptional
    -0.81
    ftagPool
    -0.78
     outstanding
    -0.74
    exception
    -0.74
     potent
    -0.74
    principalColumn
    -0.72
    sidemargin
    -0.70
     robust
    -0.70
     typique
    -0.65
    POSITIVE LOGITS
    ally
    0.70
    ly
    0.68
    ing
    0.63
    al
    0.63
    antly
    0.61
    ialmente
    0.61
    IALLY
    0.58
    ually
    0.57
    ially
    0.56
    ants
    0.55
    Activations Density 0.082%

    No Known Activations