© 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. 4-CLT-HP
    7. 429
    Prev
    Next
    INDEX
    Explanations

    internet content

    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
     naturale
    -0.47
    ngOnInit
    -0.46
    Ano
    -0.45
     MessageBoxIcon
    -0.45
    Переваги
    -0.44
     naturelle
    -0.43
     pick
    -0.43
     rosen
    -0.43
     alight
    -0.42
     {}\
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.63
    contentLoaded
    0.60
    ksikon
    0.60
     gynhyrchwyd
    0.58
    qvarna
    0.55
    стат
    0.54
    ContentAsync
    0.53
     AspNetCore
    0.53
    EndContext
    0.53
     FishBase
    0.52
    Activations Density 0.002%

    No Known Activations