© 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. 22-RES-MATRYOSHKA-DC
    7. 2377
    Prev
    Next
    INDEX
    Explanations

    the word "man" or parts of it within a word

    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
    CloseOperation
    -0.88
     للمعارف
    -0.63
     оригіналу
    -0.63
    CDCl
    -0.63
    VersionUID
    -0.62
    BURGH
    -0.61
    Šaltiniai
    -0.60
     محفوظة
    -0.60
     betweenstory
    -0.59
    PhysRevD
    -0.57
    POSITIVE LOGITS
     Man
    0.73
    Man
    0.69
     MAN
    0.68
     man
    0.63
    Mano
    0.57
     mano
    0.56
    cipation
    0.54
    made
    0.53
    handled
    0.53
    man
    0.53
    Activations Density 0.087%

    No Known Activations