© 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. 5-CLT-HP
    7. 91975
    Prev
    Next
    INDEX
    Explanations

    limiting words

    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
     CreateTagHelper
    -0.60
     biasanya
    -0.59
    Vidite
    -0.58
     otomatig
    -0.57
    textsc
    -0.56
    oa̍t
    -0.52
     purpoſe
    -0.51
     propOrder
    -0.51
    noons
    -0.51
    Daar
    -0.50
    POSITIVE LOGITS
     by
    0.82
     through
    0.79
     with
    0.73
     when
    0.73
     from
    0.69
     as
    0.67
    Atsauces
    0.65
     للمعارف
    0.64
     to
    0.63
     via
    0.63
    Activations Density 0.002%

    No Known Activations