© 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. 0-CLT-HP
    7. 92789
    Prev
    Next
    INDEX
    Explanations

    Jargon

    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
    Kapcsolódó
    -0.64
    toHaveBeenCalled
    -0.52
    ClientSize
    -0.52
     to
    -0.51
    KURZBESCHREIBUNG
    -0.51
    \{\\
    -0.47
    AndView
    -0.46
    DNEY
    -0.44
    impianto
    -0.44
    czegóły
    -0.44
    POSITIVE LOGITS
    s
    0.89
    shen
    0.66
    ing
    0.64
    sing
    0.63
    ی
    0.59
     enfans
    0.58
    she
    0.56
    sho
    0.56
    sang
    0.56
    orous
    0.56
    Activations Density 1.596%

    No Known Activations