© 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. 12-RES-MATRYOSHKA-DC
    7. 3566
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.96
     Shakspeare
    -0.96
     purpoſe
    -0.91
     becauſe
    -0.90
     Efq
    -0.90
     Chriftian
    -0.89
     ſtate
    -0.88
     Majefty
    -0.88
     venons
    -0.88
     Monfieur
    -0.88
    POSITIVE LOGITS
     be
    0.63
    tvguidetime
    0.59
     createStore
    0.55
    ls
    0.55
     Bl
    0.55
     Al
    0.54
    참고
    0.54
     Me
    0.54
     Fan
    0.54
     a
    0.53
    Activations Density 0.002%

    No Known Activations