© 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. 92198
    Prev
    Next
    INDEX
    Explanations

    formal writing snippets

    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
     setCurrent
    -0.49
    Hoje
    -0.48
     actuels
    -0.48
    Today
    -0.48
     trå
    -0.46
    ěla
    -0.46
    brtc
    -0.45
    IContainer
    -0.44
    ientôt
    -0.42
     InputDecoration
    -0.42
    POSITIVE LOGITS
    ativement
    0.68
    +:+
    0.66
    expandindo
    0.63
    MockBean
    0.60
     Roskov
    0.57
    ituary
    0.56
    श्ले
    0.55
    Abit
    0.55
    клопе
    0.54
     nakalista
    0.53
    Activations Density 0.001%

    No Known Activations