© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2798
    Prev
    Next
    INDEX
    Explanations

    impact

    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
    émie
    -0.45
    uschen
    -0.44
    تقاوى
    -0.43
    født
    -0.42
     incendios
    -0.41
     böl
    -0.40
    IX
    -0.40
    truth
    -0.39
     allgemeinen
    -0.39
     persec
    -0.39
    POSITIVE LOGITS
     similar
    0.71
     that
    0.70
     BorderSide
    0.68
     BoxDecoration
    0.68
     similaire
    0.66
    AnchorStyles
    0.65
    pezi
    0.61
     analogous
    0.59
    tonsoft
    0.59
     equivalent
    0.59
    Activations Density 0.001%

    No Known Activations