© 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. 5-CLT-HP
    7. 91842
    Prev
    Next
    INDEX
    Explanations

    banknotes

    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
    SourceChecksum
    -0.69
    :✨
    -0.57
    DebuggerNonUser
    -0.56
    Datuak
    -0.52
     kasarigan
    -0.49
    StoryboardSegue
    -0.49
    PYX
    -0.46
    arXiv
    -0.45
     متعلقه
    -0.45
     jäsen
    -0.45
    POSITIVE LOGITS
     mol
    0.57
     Modular
    0.56
     للمعارف
    0.54
     PIA
    0.53
     gmina
    0.53
     Vox
    0.53
    pédie
    0.52
    zzleHttp
    0.52
     MO
    0.50
     Процитовано
    0.50
    Activations Density 0.001%

    No Known Activations