© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1572
    Prev
    Next
    INDEX
    Explanations

    words that begin with the "ph" sound

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <tr>
    -0.68
     ples
    -0.68
    par
    -0.67
    ostok
    -0.66
    Lain
    -0.61
    ונ
    -0.60
    Rao
    -0.60
     نق
    -0.59
    Lei
    -0.59
    ><
    -0.59
    POSITIVE LOGITS
     Ph
    1.58
    Ph
    1.48
     ph
    1.45
     PH
    1.45
     Phillies
    1.36
    PH
    1.35
    ph
    1.34
     Phaser
    1.34
     Φ
    1.30
     φ
    1.30
    Activations Density 0.885%

    No Known Activations