© 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. 94326
    Prev
    Next
    INDEX
    Explanations

    discovered

    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
     discovered
    -1.04
     Discovered
    -0.96
     discover
    -0.85
     scoperto
    -0.81
    discovered
    -0.79
     découverte
    -0.70
    discover
    -0.70
     descubrió
    -0.68
    Discover
    -0.67
     esternos
    -0.65
    POSITIVE LOGITS
     the
    0.73
     onCreateView
    0.57
    makeConstraints
    0.53
     he
    0.49
    mbggenerated
    0.48
    adering
    0.47
    ietf
    0.47
     Fuller
    0.46
    ]")]
    0.46
    msgid
    0.46
    Activations Density 1.099%

    No Known Activations