© 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. 1438
    Prev
    Next
    INDEX
    Explanations

    programming/language descriptions

    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
     —
    -0.59
     ketiga
    -0.58
     Five
    -0.54
     saying
    -0.53
     five
    -0.51
     four
    -0.51
     keempat
    -0.51
     three
    -0.51
    ✨:
    -0.50
     mentioned
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.77
    Rhestr
    0.70
     continúas
    0.68
    UnusedPrivate
    0.68
     henvisninger
    0.67
    rungsseite
    0.65
    IsMutable
    0.64
    ąz
    0.63
    verwijspagina
    0.61
     ddelweddau
    0.61
    Activations Density 0.000%

    No Known Activations