© 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. 90602
    Prev
    Next
    INDEX
    Explanations

    him

    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
     him
    -3.22
    him
    -2.03
     his
    -1.86
     he
    -1.81
     él
    -1.63
     ihm
    -1.55
     lui
    -1.52
     ihn
    -1.47
     ему
    -1.40
    彼は
    -1.27
    POSITIVE LOGITS
     Shakspeare
    1.22
    AndEndTag
    1.02
     Shaksp
    1.02
     Theſe
    0.99
     ་་
    0.97
     myſelf
    0.97
    ſelf
    0.96
     Mahomet
    0.96
     doubtnut
    0.93
     poffible
    0.91
    Activations Density 0.049%

    No Known Activations