© 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. 0-CLT-HP
    4. 1871
    Prev
    Next
    INDEX
    Explanations

    Ple

    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
     Gil
    -0.74
    itary
    -0.62
     Ple
    -0.60
    s
    -0.59
     the
    -0.54
    vax
    -0.54
    sac
    -0.54
    PYX
    -0.53
     Sac
    -0.51
     De
    -0.50
    POSITIVE LOGITS
    المناصب
    0.83
    المكان
    0.79
     avoient
    0.72
    Enders
    0.71
     crdi
    0.70
     Majefty
    0.68
     ―――――
    0.66
     originaux
    0.66
     fathoms
    0.65
     Efq
    0.65
    Activations Density 0.210%

    No Known Activations