© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    the word "ha"

    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
    Negative Logits
    Билгалдахарш
    -0.65
    onges
    -0.63
     MNRAS
    -0.60
    multipart
    -0.57
     Profile
    -0.57
     Logic
    -0.56
    dji
    -0.56
     razu
    -0.56
    Примітки
    -0.55
    totic
    -0.54
    POSITIVE LOGITS
     ha
    0.69
     ویکی‌پدیا
    0.55
    Ha
    0.55
     Ha
    0.54
     AppCompatTheme
    0.53
    ArgsConstructor
    0.53
     HA
    0.52
    UnusedPrivate
    0.48
    Hahahahaha
    0.48
    Jeografia
    0.47
    Activations Density 0.076%

    No Known Activations