© 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. 1710
    Prev
    Next
    INDEX
    Explanations

    threat

    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
    stdafx
    -0.53
    .
    -0.49
     urbanas
    -0.47
    +#+
    -0.47
     decorativas
    -0.46
     sehingga
    -0.45
     casó
    -0.44
    Lähteet
    -0.44
    цтва
    -0.43
     поскольку
    -0.43
    POSITIVE LOGITS
     the
    0.90
     to
    0.70
     collapse
    0.66
     loss
    0.62
     our
    0.61
    adaptiveStyles
    0.59
     sudden
    0.59
     survival
    0.57
    oredCriteria
    0.57
     collapsing
    0.56
    Activations Density 0.003%

    No Known Activations