© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2111
    Prev
    Next
    INDEX
    Explanations

    -

    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
    enso
    -0.56
    ness
    -0.52
    vex
    -0.52
    matchCondition
    -0.51
    ën
    -0.49
     Horses
    -0.49
    noe
    -0.48
     ofs
    -0.48
     Shells
    -0.47
    jectures
    -0.46
    POSITIVE LOGITS
    MemoryWarning
    0.57
    abank
    0.55
    StoreMessageInfo
    0.55
    away
    0.54
    able
    0.52
     NUKAT
    0.51
    Composable
    0.50
    abo
    0.49
     חיצוניים
    0.48
    AutoField
    0.48
    Activations Density 0.002%

    No Known Activations