© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2963
    Prev
    Next
    INDEX
    Explanations

    words starting with "hist" broadly pertaining to history and histology

    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
    AddTagHelper
    -0.72
     WaitForSeconds
    -0.64
     nahilalakip
    -0.63
    MigrationBuilder
    -0.60
     Infantil
    -0.60
    Obrázky
    -0.60
    addPreferredGap
    -0.59
    EMPL
    -0.59
    Gambas
    -0.58
    ędzynarod
    -0.57
    POSITIVE LOGITS
    SequentialGroup
    0.70
    چه
    0.65
     useHistory
    0.63
     books
    0.58
     болезни
    0.57
    悠
    0.54
     boyunca
    0.54
     panjang
    0.52
    unknownFields
    0.51
    lapi
    0.48
    Activations Density 0.076%

    No Known Activations