© 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. 9761
    Prev
    Next
    INDEX
    Explanations

    tanks

    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
    postsleuth
    -0.76
    TagMode
    -0.74
    LookAnd
    -0.73
    تقاوى
    -0.69
     متعلقه
    -0.66
    Diwedd
    -0.66
     kasarigan
    -0.66
     MotionEvent
    -0.65
     JpaRepository
    -0.63
     onCancelled
    -0.62
    POSITIVE LOGITS
     thermocouple
    0.45
     stra
    0.45
     holding
    0.44
     juſ
    0.44
     ItemStack
    0.43
    GPP
    0.43
     utafitiHapana
    0.43
     of
    0.43
    เท
    0.42
     core
    0.41
    Activations Density 0.012%

    No Known Activations