© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 936
    Prev
    Next
    INDEX
    Explanations

    past tense verbs or adjectives, often with suffixes like "-ed" or variants of "search".

    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.22.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.22.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
    httphttps
    -0.99
     CreateTagHelper
    -0.93
    enumi
    -0.85
    GraphicsUnit
    -0.85
     متعلقه
    -0.82
    //
    -0.78
    AndEndTag
    -0.77
    withIdentifier
    -0.76
     שוליים
    -0.76
    ioutil
    -0.75
    POSITIVE LOGITS
    ness
    0.76
     вами
    0.70
     हुआ
    0.69
    own
    0.68
     by
    0.67
     мной
    0.66
     нами
    0.63
     हुई
    0.63
    NESS
    0.63
     przez
    0.62
    Activations Density 1.505%

    No Known Activations