© 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. 2360
    Prev
    Next
    INDEX
    Explanations

    the word "I" and its variations, indicating a focus on personal perspective or subjective statements

    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
    s
    -0.61
     on
    -0.58
    Susanne
    -0.56
    pust
    -0.51
     скоро
    -0.49
     bild
    -0.48
    ParentId
    -0.48
     inside
    -0.48
     in
    -0.47
     Sharpe
    -0.46
    POSITIVE LOGITS
    httphttps
    1.25
    تقاوى
    1.15
     ioutil
    1.08
    awtextra
    1.03
    tagext
    0.97
     MainAxisSize
    0.95
    ագրություններ
    0.89
    raisemb
    0.88
    tvguidetime
    0.85
     AdapterView
    0.85
    Activations Density 0.057%

    No Known Activations