© 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. 1-CLT-HP
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    rystal

    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
    oughly
    -0.67
    rystal
    -0.59
    complexType
    -0.52
     recrystal
    -0.47
    tagHelperRunner
    -0.43
    omst
    -0.42
     min
    -0.42
    anmoins
    -0.41
    less
    -0.40
    usis
    -0.40
    POSITIVE LOGITS
     SwitchCompat
    0.66
    ValueGeneration
    0.65
     femininas
    0.64
     myſelf
    0.62
    جغرافيا
    0.62
     Efq
    0.62
     VIAF
    0.61
     ostavi
    0.60
     jubilee
    0.59
    ImageField
    0.59
    Activations Density 0.012%

    No Known Activations