© 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. 1-CLT-HP
    7. 12456
    Prev
    Next
    INDEX
    Explanations

    flowers and descriptive words

    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
    lamydia
    -0.40
    ابراین
    -0.38
    AGH
    -0.37
    ̸
    -0.36
    taje
    -0.36
     norte
    -0.36
    sement
    -0.36
     Maier
    -0.35
     trofeo
    -0.35
     però
    -0.35
    POSITIVE LOGITS
     '\\;'
    0.83
    Personendaten
    0.77
     resourceCulture
    0.75
    oredCriteria
    0.73
    RTEE
    0.71
     autorytatywna
    0.70
    ftagPool
    0.69
    MigrationBuilder
    0.69
     okuyayım
    0.68
    odils
    0.68
    Activations Density 0.040%

    No Known Activations