© 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. 0-CLT-HP
    7. 90917
    Prev
    Next
    INDEX
    Explanations

    oxidation/legal

    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
    sohn
    -1.01
     OBB
    -0.93
    URLException
    -0.88
     Theſe
    -0.84
     myſelf
    -0.84
    RectangleBorder
    -0.83
     itſelf
    -0.83
    providedIn
    -0.82
    TestBed
    -0.82
     Efq
    -0.82
    POSITIVE LOGITS
     száz
    0.43
    Na
    0.38
    だけでも
    0.37
    L
    0.37
     Na
    0.36
    tymologie
    0.36
     
    0.36
    ore
    0.36
    di
    0.35
     \
    0.35
    Activations Density 0.182%

    No Known Activations