© 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. 20-CLT-HP
    7. 73475
    Prev
    Next
    INDEX
    Explanations

    code/niche topics

    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
     fieldNum
    -0.77
     '\\;'
    -0.75
     wireType
    -0.72
    ineno
    -0.65
     Continu
    -0.61
    ⓧ
    -0.59
     estimés
    -0.57
     Celeste
    -0.57
     Olds
    -0.57
    BeginContext
    -0.56
    POSITIVE LOGITS
     expédi
    0.49
     rowspan
    0.46
     BoxDecoration
    0.44
    MLLoader
    0.40
     Audiodateien
    0.40
    SequentialGroup
    0.40
    icoot
    0.40
     misión
    0.40
     marche
    0.39
     écl
    0.39
    Activations Density 0.001%

    No Known Activations