© 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. 20-CLT-HP
    7. 72807
    Prev
    Next
    INDEX
    Explanations

    Sk

    np_max-act-logits · 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
    ChildScrollView
    -0.59
    issance
    -0.53
    ніципалі
    -0.52
    AddTagHelper
    -0.52
    sino
    -0.51
     spit
    -0.50
    entri
    -0.50
     TestBed
    -0.50
    bootstrapcdn
    -0.49
    니다
    -0.49
    POSITIVE LOGITS
    lgari
    0.66
    astify
    0.62
     виправивши
    0.57
     насељу
    0.47
     قل
    0.47
     posibil
    0.47
    dags
    0.47
    amani
    0.47
     Doble
    0.46
    onAdd
    0.46
    Activations Density 0.001%

    No Known Activations