© 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. 24-RES-MATRYOSHKA-DC
    7. 84
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences, especially in scientific writing

    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/blocks.24.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.24.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
     she
    -0.74
     police
    -0.73
     him
    -0.71
     defendant
    -0.70
     former
    -0.68
     men
    -0.68
     appellant
    -0.66
     shes
    -0.65
     second
    -0.65
     her
    -0.65
    POSITIVE LOGITS
     The
    1.60
     This
    1.58
     However
    1.54
     These
    1.45
     In
    1.41
     It
    1.38
     There
    1.38
     Although
    1.36
     While
    1.35
     Furthermore
    1.32
    Activations Density 4.475%

    No Known Activations