© 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. 2916
    Prev
    Next
    INDEX
    Explanations

    Defaultsass

    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
    __':
    -0.76
    تقاوى
    -0.73
     незавершена
    -0.71
    RenderAtEndOf
    -0.68
    Bibliografie
    -0.66
    __':
    -0.64
     otomatig
    -0.64
     CURIAM
    -0.64
     nakalista
    -0.63
    脚注の使い方
    -0.63
    POSITIVE LOGITS
     The
    0.48
     fede
    0.46
     the
    0.45
     propre
    0.43
     further
    0.43
     propres
    0.41
     gouver
    0.39
     parcial
    0.38
    दार
    0.38
     tava
    0.38
    Activations Density 0.005%

    No Known Activations