© 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. 97062
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
     pulumi
    -0.58
    рення
    -0.57
    DetailComponent
    -0.51
    SourceChecksum
    -0.50
     in
    -0.50
    řízení
    -0.50
    Mutagenicity
    -0.49
    skip
    -0.48
    ivir
    -0.48
     "..\..\
    -0.47
    POSITIVE LOGITS
     things
    0.83
     كومونز
    0.70
     interesting
    0.66
     matters
    0.65
     conclusions
    0.65
     issues
    0.63
     questions
    0.63
     points
    0.61
     observations
    0.61
     surprises
    0.60
    Activations Density 0.007%

    No Known Activations