© 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. 2753
    Prev
    Next
    INDEX
    Explanations

    way

    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
     begitu
    -0.45
     demikian
    -0.41
    ながら
    -0.41
    ђа
    -0.40
    edos
    -0.40
     väga
    -0.40
    ään
    -0.40
    cutta
    -0.39
     Voiture
    -0.39
    helin
    -0.38
    POSITIVE LOGITS
     of
    1.27
    tagHelperRunner
    0.92
    providedIn
    0.87
    rawDesc
    0.82
     you
    0.72
    RectangleBorder
    0.68
     lies
    0.66
    of
    0.66
    ]++;
    0.66
    ของ
    0.66
    Activations Density 0.001%

    No Known Activations