© 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. 43219
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     stalked
    -1.01
     itſelf
    -0.76
     Efq
    -0.67
     marquées
    -0.65
     Theſe
    -0.65
     himſelf
    -0.60
     themſelves
    -0.60
     ſhe
    -0.58
     myſelf
    -0.57
    atever
    -0.56
    POSITIVE LOGITS
    хьтан
    0.65
    StoryboardSegue
    0.64
    TagHelper
    0.59
    RunAsync
    0.59
     kaynağından
    0.58
     CreateTagHelper
    0.58
    umman
    0.56
    KommentareTeilen
    0.53
     kaarangay
    0.52
    TagHelpers
    0.52
    Activations Density 1.083%

    No Known Activations