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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44157
    Prev
    Next
    INDEX
    Explanations

    homogen

    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
    s
    -0.67
    <eos>
    -0.62
     ra
    -0.60
     R
    -0.59
     A
    -0.58
     F
    -0.56
     Sp
    -0.56
     De
    -0.56
     D
    -0.55
     dan
    -0.55
    POSITIVE LOGITS
     Efq
    1.29
     myſelf
    1.29
     Theſe
    1.24
     Anſ
    1.20
     Reſ
    1.20
     Majefty
    1.20
     itſelf
    1.20
     ―――――
    1.16
     Monfieur
    1.16
     pleaſure
    1.15
    Activations Density 0.277%

    No Known Activations