© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97224
    Prev
    Next
    INDEX
    Explanations

    trol

    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
     myſelf
    -1.13
     Majefty
    -1.06
     Shakspeare
    -1.02
     pleaſure
    -1.01
    verwijspagina
    -0.98
     purpoſe
    -0.98
     itſelf
    -0.98
     Ptole
    -0.96
     ſhe
    -0.94
     themſelves
    -0.94
    POSITIVE LOGITS
    s
    2.20
    ی
    1.40
    i
    1.23
    e
    1.23
    a
    1.18
    o
    1.15
    es
    0.99
    er
    0.98
    y
    0.92
    en
    0.88
    Activations Density 0.336%

    No Known Activations