© 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. 840
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific lowercase letter

    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
     L
    -0.70
     LAC
    -0.66
     Л
    -0.63
     cherchés
    -0.63
     Labyrinth
    -0.63
    ManagedBean
    -0.63
    titleMargin
    -0.61
    AsUp
    -0.59
    Personendaten
    -0.59
    SequentialGroup
    -0.59
    POSITIVE LOGITS
    l
    2.72
    ls
    1.15
    lty
    1.15
    lO
    1.14
    lI
    1.13
     l
    1.08
    lm
    0.99
    lt
    0.98
    lh
    0.97
    lde
    0.97
    Activations Density 0.245%

    No Known Activations