© 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. 5-CLT-HP
    7. 93016
    Prev
    Next
    INDEX
    Explanations

    to

    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
    yntaxException
    -0.52
     словарь
    -0.49
    TypedDataSet
    -0.47
    וויק
    -0.45
     estimés
    -0.44
     irmãos
    -0.44
    findpost
    -0.44
     hermanos
    -0.43
    ModelBuilder
    -0.43
     $\
    -0.41
    POSITIVE LOGITS
     poffe
    0.75
     ſever
    0.70
     neceff
    0.67
     purpoſe
    0.66
     tdci
    0.65
     fubject
    0.65
     occaf
    0.65
     gitara
    0.65
     lances
    0.63
    ")));
    0.62
    Activations Density 0.000%

    No Known Activations