© 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. 1-CLT-HP
    7. 14331
    Prev
    Next
    INDEX
    Explanations

    sentence

    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
     Sentence
    -0.78
     sentence
    -0.75
    Sentence
    -0.69
    sentence
    -0.67
     Sentences
    -0.63
     sentenced
    -0.59
    học
    -0.55
     financières
    -0.53
    sentences
    -0.53
     Völ
    -0.52
    POSITIVE LOGITS
    LookAnd
    0.53
     answers
    0.51
     CGFloat
    0.49
     prompts
    0.49
     matches
    0.48
    TagMode
    0.47
     resourceCulture
    0.46
    IActionResult
    0.46
     Zweiten
    0.45
     ExecuteAsync
    0.45
    Activations Density 0.002%

    No Known Activations