© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97985
    Prev
    Next
    INDEX
    Explanations

    fe

    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
    .
    -0.35
     or
    -0.34
     (
    -0.33
    НГ
    -0.31
     п
    -0.31
    Prologue
    -0.30
     đ
    -0.30
    Ethnicity
    -0.30
     o
    -0.29
    ings
    -0.29
    POSITIVE LOGITS
    <bos>
    1.23
     raiſ
    0.98
     myſelf
    0.96
     Monfieur
    0.96
    +#+#
    0.95
     Theſe
    0.95
    GEBURTSDATUM
    0.94
     uſe
    0.91
    Jereo
    0.90
     Anſ
    0.89
    Activations Density 0.085%

    No Known Activations