© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96040
    Prev
    Next
    INDEX
    Explanations

    creation/establishment

    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
     Chwiliwch
    -0.93
     AssemblyCulture
    -0.83
     виправивши
    -0.83
    tvguidetime
    -0.80
     يتيمه
    -0.79
     kasarigan
    -0.74
    verwijspagina
    -0.73
    таратура
    -0.73
     autorytatywna
    -0.73
     kaarangay
    -0.72
    POSITIVE LOGITS
     it
    1.07
     his
    0.85
     the
    0.77
     its
    0.73
     what
    0.60
     this
    0.57
     many
    0.55
     a
    0.51
     both
    0.47
    his
    0.46
    Activations Density 0.001%

    No Known Activations