© 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. 654
    Prev
    Next
    INDEX
    Explanations

    to

    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
     riuscito
    -0.46
     riusc
    -0.46
    ofluor
    -0.43
     evitando
    -0.41
    roy
    -0.41
     избежать
    -0.41
     hindering
    -0.40
    Descri
    -0.40
     killing
    -0.39
    track
    -0.38
    POSITIVE LOGITS
    <bos>
    0.85
    بوابة
    0.82
     فريبيس
    0.77
    enumi
    0.77
    UnusedPrivate
    0.74
    XDECREF
    0.66
     Waray
    0.65
    */;
    0.65
    glUniform
    0.65
     AssemblyVersion
    0.64
    Activations Density 0.074%

    No Known Activations