© 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. 2-RES-MATRYOSHKA-DC
    7. 2837
    Prev
    Next
    INDEX
    Explanations

    specific pitch values in a sequence

    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
     disponibilités
    -0.77
     Faure
    -0.72
    complexContent
    -0.66
    ocere
    -0.65
    Географиясе
    -0.65
     Linder
    -0.65
    %");
    -0.63
     Meksiku
    -0.62
     Bü
    -0.61
    AFTA
    -0.61
    POSITIVE LOGITS
     pitch
    3.88
     Pitch
    3.59
    pitch
    3.52
    Pitch
    3.48
     pitches
    3.30
     pitched
    3.05
     pitching
    2.97
    pitched
    2.55
    Pit
    1.87
     Pit
    1.80
    Activations Density 0.015%

    No Known Activations