© 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. 20-CLT-HP
    7. 71844
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · 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
    elemField
    -0.68
    Show
    -0.56
     Show
    -0.55
    ValueStyle
    -0.54
     Explain
    -0.53
    fail
    -0.53
     explain
    -0.51
    UDES
    -0.51
    Aholisi
    -0.49
     SqlCommand
    -0.49
    POSITIVE LOGITS
     handle
    0.74
     leverage
    0.63
    SOUNDBITE
    0.59
    EDEFAULT
    0.58
     process
    0.58
    :✨
    0.57
    Atentamente
    0.56
     store
    0.55
    handle
    0.54
    cyj
    0.54
    Activations Density 0.003%

    No Known Activations