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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16297
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for."

    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
    +#+#
    -0.81
    RenderAtEndOf
    -0.73
     becauſe
    -0.73
     صوتيه
    -0.72
     Normdatei
    -0.70
     HttpNotFound
    -0.64
     linkovi
    -0.62
     resourceCulture
    -0.62
    devamını
    -0.61
    TagMode
    -0.61
    POSITIVE LOGITS
    IVEREF
    0.66
     no
    0.56
     calendriers
    0.55
     a
    0.52
     its
    0.51
     <
    0.50
     ample
    0.48
    mada
    0.47
    EMPL
    0.47
     some
    0.47
    Activations Density 0.008%

    No Known Activations