© 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. 0-CLT-HP
    7. 40087
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Martel
    -2.42
     Dietz
    -1.55
     beginnetje
    -0.82
    ValueStyle
    -0.78
     '\\;'
    -0.77
    StructEnd
    -0.73
     Vikipedi
    -0.71
    principalColumn
    -0.71
    TagHelper
    -0.66
    odin
    -0.65
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.62
    sel
    0.43
     כה
    0.43
    prüche
    0.42
    toks
    0.42
     Ask
    0.41
    łow
    0.41
     Misch
    0.41
    URIDAD
    0.41
     parach
    0.41
    Activations Density 1.170%

    No Known Activations