© 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. 71719
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     ProtoMessage
    -0.77
     betweenstory
    -0.65
    ponses
    -0.65
     typelib
    -0.64
     Combien
    -0.62
     wireType
    -0.62
    SharedDtor
    -0.60
    InputBorder
    -0.60
    +#+#
    -0.60
     téléphonique
    -0.59
    POSITIVE LOGITS
     cross
    0.50
     head
    0.48
    cross
    0.48
     range
    0.48
    RANGE
    0.47
     diberi
    0.47
    heads
    0.47
    िन्न
    0.46
     inclusive
    0.46
    bringer
    0.45
    Activations Density 0.001%

    No Known Activations