© 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. 4-CLT-HP
    7. 2788
    Prev
    Next
    INDEX
    Explanations

    the thing itself

    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
     itself
    -1.00
     themselves
    -0.92
    themselves
    -0.91
    itself
    -0.91
     Itself
    -0.81
     himself
    -0.77
    himself
    -0.74
     herself
    -0.73
    本身
    -0.71
     sendiri
    -0.70
    POSITIVE LOGITS
    CPtr
    0.82
    ỡng
    0.78
    AndroidJUnit
    0.76
     autorytatywna
    0.75
    ⓘ
    0.74
     NSCoder
    0.74
     defaultstate
    0.73
    resave
    0.73
    setupUi
    0.73
    żesz
    0.73
    Activations Density 0.010%

    No Known Activations