© 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. 93357
    Prev
    Next
    INDEX
    Explanations

    Degree/comparison

    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
    ngdoc
    -0.65
     supérieurs
    -0.60
    ագրություններ
    -0.54
     lèvres
    -0.52
     jugé
    -0.52
     genoux
    -0.52
     prisonniers
    -0.52
     correctes
    -0.51
     blessés
    -0.49
     payé
    -0.48
    POSITIVE LOGITS
     the
    0.65
     those
    0.58
     Dra
    0.58
     individual
    0.58
    principalTable
    0.57
     how
    0.57
    zad
    0.57
     Min
    0.56
     some
    0.55
     what
    0.55
    Activations Density 0.012%

    No Known Activations