© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1043
    Prev
    Next
    INDEX
    Explanations

    last

    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
    ()");
    -0.55
    gnore
    -0.52
     demikian
    -0.52
     kasarigan
    -0.51
     casó
    -0.50
     nuevamente
    -0.49
     intptr
    -0.49
    enumi
    -0.49
    IntoConstraints
    -0.49
     dalej
    -0.48
    POSITIVE LOGITS
     time
    0.84
     to
    0.69
    <bos>
    0.67
     was
    0.66
     thing
    0.65
     data
    0.60
     incident
    0.59
     person
    0.58
     study
    0.58
     news
    0.57
    Activations Density 0.003%

    No Known Activations