© 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. 932
    Prev
    Next
    INDEX
    Explanations

    s

    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
    GEBURTSDATUM
    -0.65
    IntoConstraints
    -0.65
    typeorm
    -0.65
     createSlice
    -0.63
    kään
    -0.62
    NewUrlParser
    -0.59
    Understand
    -0.59
    >{@
    -0.58
     Understand
    -0.57
     digitais
    -0.57
    POSITIVE LOGITS
     both
    0.63
     each
    0.56
    both
    0.53
    jmniej
    0.48
     Both
    0.47
    URLException
    0.45
    Both
    0.45
    各
    0.45
    each
    0.45
     BOTH
    0.44
    Activations Density 0.005%

    No Known Activations