© 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. 2799
    Prev
    Next
    INDEX
    Explanations

    blood

    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
     فريبيس
    -1.10
     חיצוניים
    -0.92
    writeField
    -0.89
    Composable
    -0.86
     الحره
    -0.80
    ftagPool
    -0.80
    ########.
    -0.78
    oneofs
    -0.77
    TagMode
    -0.75
     estekak
    -0.74
    POSITIVE LOGITS
    borne
    0.37
    Denn
    0.34
    mpton
    0.34
    full
    0.34
    volves
    0.34
    shot
    0.34
    compatible
    0.33
    ÄT
    0.33
     j
    0.33
    ül
    0.33
    Activations Density 0.002%

    No Known Activations