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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3105
    Prev
    Next
    INDEX
    Explanations

    except

    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
     they
    -0.56
     împre
    -0.56
    킵
    -0.55
    you
    -0.54
    there
    -0.53
     käyt
    -0.53
    presso
    -0.52
     you
    -0.52
     there
    -0.52
     it
    -0.51
    POSITIVE LOGITS
     GenerationType
    0.92
    LookAnd
    0.91
    sizeCache
    0.76
    createCanvas
    0.72
    ErrorListener
    0.68
    principalTable
    0.67
    GeneratedValue
    0.63
    Autoritní
    0.62
    XmlSchema
    0.59
    ActiveRecord
    0.59
    Activations Density 0.003%

    No Known Activations