© 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. 0-CLT-HP
    4. 97738
    Prev
    Next
    INDEX
    Explanations

    names and specialized vocabulary

    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
     Friedrich
    -0.67
    rea
    -0.66
    zak
    -0.52
    REA
    -0.52
    Friedrich
    -0.50
     familiale
    -0.50
     pleaſure
    -0.49
     *++
    -0.48
     prieten
    -0.46
     glede
    -0.46
    POSITIVE LOGITS
    Naissance
    0.70
     resourceCulture
    0.67
    WriteBarrier
    0.66
    awtextra
    0.65
    IVEREF
    0.61
    msgTypes
    0.60
    umoj
    0.58
    Lähteet
    0.57
    IContainer
    0.57
     initComponents
    0.56
    Activations Density 1.659%

    No Known Activations