© 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. 25693
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and related phrases expressing personal experiences or actions

    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
     kaynağından
    -0.95
     '\\;'
    -0.94
    ClientSize
    -0.89
    تقاوى
    -0.87
    "]);
    -0.87
    InjectAttribute
    -0.84
    AndEndTag
    -0.83
    >");
    -0.82
    IntoConstraints
    -0.79
    '));
    -0.78
    POSITIVE LOGITS
    Ranks
    0.45
     Lumpur
    0.45
    datei
    0.44
    orph
    0.44
    denly
    0.42
    bours
    0.42
     урна
    0.41
    bede
    0.41
     Ud
    0.40
    ecake
    0.40
    Activations Density 0.023%

    No Known Activations