© 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. 1-CLT-HP
    7. 14397
    Prev
    Next
    INDEX
    Explanations

    craft

    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
    argin
    -0.47
    Geplaatst
    -0.46
    oto
    -0.44
     fra
    -0.44
    росло
    -0.43
    agen
    -0.43
    গ্র
    -0.42
    jeto
    -0.42
     aio
    -0.42
    datastore
    -0.41
    POSITIVE LOGITS
     فريبيس
    0.68
    BagLayout
    0.61
     doubtnut
    0.60
    viewDid
    0.60
    MemoryWarning
    0.59
    nologue
    0.59
     IBOutlet
    0.59
     الحره
    0.59
     Efq
    0.59
     الدولى
    0.58
    Activations Density 0.044%

    No Known Activations