© 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. 9268
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Referencies
    -0.73
     MainAxisSize
    -0.68
    calça
    -0.67
    DIPSETTING
    -0.66
    %)$
    -0.64
     AttributeSet
    -0.64
     forState
    -0.64
    guous
    -0.63
     MonoBehaviour
    -0.61
     হয়
    -0.60
    POSITIVE LOGITS
    NOPQRST
    0.54
    astéroïdes
    0.50
     متعلقه
    0.50
    Ĝ
    0.48
    MemoryWarning
    0.48
    IsMutable
    0.47
    ArrowToggle
    0.45
    InstrumentedTest
    0.42
     betweenstory
    0.41
     sty
    0.41
    Activations Density 0.182%

    No Known Activations