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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 448
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter "H," especially when used as a standalone uppercase letter or in contexts emphasizing "H" with high emphasis

    oai_token-act-pair · gpt-4.1-nano
    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
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    -0.60
    kloped
    -0.60
    astify
    -0.49
     necesite
    -0.47
    wój
    -0.47
    ommer
    -0.46
     vayas
    -0.44
     iprot
    -0.44
     jaya
    -0.44
    albero
    -0.44
    POSITIVE LOGITS
     H
    2.95
    H
    2.92
     h
    2.56
    h
    2.33
    setH
    1.84
    Ｈ
    1.77
    Hs
    1.52
    Hh
    1.46
    mH
    1.41
    rH
    1.41
    Activations Density 1.897%

    No Known Activations