© 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. 0-CLT-HP
    7. 94501
    Prev
    Next
    INDEX
    Explanations

    gaseous, optional contexts

    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
    optional
    -0.83
    AddTagHelper
    -0.77
     optional
    -0.74
     possíveis
    -0.73
     posibles
    -0.71
    labili
    -0.69
    opcional
    -0.69
    possible
    -0.68
    Possible
    -0.67
     opcional
    -0.67
    POSITIVE LOGITS
    ']))
    0.57
    )|^{
    0.57
    +#+
    0.55
    cratic
    0.53
    hoid
    0.51
    )))));
    0.49
    pted
    0.49
     PMI
    0.48
     frontal
    0.48
     modus
    0.47
    Activations Density 0.125%

    No Known Activations