© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93472
    Prev
    Next
    INDEX
    Explanations

    Uncertainty/incomplete actions

    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
     buone
    -0.63
     amanhã
    -0.61
    gantung
    -0.60
     coû
    -0.59
     umana
    -0.59
     médicale
    -0.59
     sauvages
    -0.58
     tasche
    -0.57
     ingredienti
    -0.57
     ochi
    -0.57
    POSITIVE LOGITS
    <bos>
    0.58
     see
    0.57
     have
    0.53
     realize
    0.53
    onoi
    0.50
    itudinal
    0.50
     think
    0.49
     consider
    0.48
     realise
    0.47
    hoga
    0.46
    Activations Density 0.035%

    No Known Activations