© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    groups of letters, particularly in a context related to patterns or probabilities of selection

    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
    makeConstraints
    -0.98
     propOrder
    -0.87
    Lähteet
    -0.86
    mylist
    -0.79
    Alike
    -0.78
    avigation
    -0.73
     onPostExecute
    -0.73
    uesday
    -0.72
    ConstraintMaker
    -0.71
     Roskov
    -0.70
    POSITIVE LOGITS
     letters
    1.66
     Letters
    1.63
    Letters
    1.52
     LETTERS
    1.47
    letters
    1.42
     Letter
    1.39
     LETTER
    1.38
    letter
    1.35
    LETTER
    1.33
    Letter
    1.31
    Activations Density 0.043%

    No Known Activations