© 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. 97553
    Prev
    Next
    INDEX
    Explanations

    whatever

    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
    脚注の使い方
    -0.76
     Мексичка
    -0.55
    stdc
    -0.52
     contextLoads
    -0.51
     himo
    -0.50
     figliu
    -0.47
     NKC
    -0.47
     SearchView
    -0.47
     Akismet
    -0.47
    IonicModule
    -0.47
    POSITIVE LOGITS
     you
    0.64
    mendation
    0.57
     كومونز
    0.55
    antaranya
    0.55
    lás
    0.54
    agory
    0.53
    {}/
    0.52
     nation
    0.52
     we
    0.51
    eseorang
    0.51
    Activations Density 0.002%

    No Known Activations