© 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. 43466
    Prev
    Next
    INDEX
    Explanations

    em

    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
    em
    -1.89
    Em
    -1.68
     em
    -1.67
     Em
    -1.63
    EM
    -1.56
     EM
    -1.45
    emb
    -1.01
    emp
    -0.99
     emp
    -0.97
     Emp
    -0.93
    POSITIVE LOGITS
     Anſ
    0.88
     doubtnut
    0.88
     Shakspeare
    0.88
     itſelf
    0.85
     Efq
    0.85
    ſelves
    0.83
     Shaksp
    0.81
     Houſe
    0.80
     Majefty
    0.79
    ſelf
    0.79
    Activations Density 1.391%

    No Known Activations