© 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. 5-CLT-HP
    7. 96868
    Prev
    Next
    INDEX
    Explanations

    ronom

    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
    <bos>
    -0.61
    CROSSTALK
    -0.43
    '
    -0.43
     football
    -0.41
     Obst
    -0.40
     aniversário
    -0.40
     m
    -0.40
    ho
    -0.40
     Matthews
    -0.39
    rit
    -0.39
    POSITIVE LOGITS
     pinulongan
    0.96
    tagHelperRunner
    0.84
    Personensuche
    0.83
     незавершена
    0.83
     nahilalakip
    0.76
    MigrationBuilder
    0.71
     CreateTagHelper
    0.69
    EndInit
    0.68
    Diweddarwch
    0.68
    Rohy
    0.67
    Activations Density 0.003%

    No Known Activations