© 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. 13393
    Prev
    Next
    INDEX
    Explanations

    charity

    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
    LookAnd
    -0.85
    enumii
    -0.68
    eadilan
    -0.66
    :])
    -0.62
    honor
    -0.60
    enumi
    -0.59
     "..\..\..\
    -0.58
     Accommodations
    -0.57
    humor
    -0.57
    Honors
    -0.57
    POSITIVE LOGITS
    WebVitals
    0.55
     doInBackground
    0.52
    <thead>
    0.50
    Referanser
    0.50
     with
    0.49
     Gough
    0.47
    ibase
    0.47
     on
    0.47
    uebas
    0.46
    jsh
    0.45
    Activations Density 0.009%

    No Known Activations