© 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. 12-RES-MATRYOSHKA-DC
    7. 20079
    Prev
    Next
    INDEX
    Explanations

    phrases indicating formal announcements or statements by organizations or authorities

    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
    enterOuterAlt
    -0.73
     للاسماء
    -0.66
     חיצוניים
    -0.63
     bezeichneter
    -0.63
    HideFlags
    -0.60
     препратки
    -0.58
    ]")]
    -0.57
    endphp
    -0.55
    Soorten
    -0.55
     논
    -0.55
    POSITIVE LOGITS
     fanfare
    0.60
    mitteilung
    0.59
     announcement
    0.56
     release
    0.56
    PRNewswire
    0.54
     releases
    0.52
     Tweet
    0.52
     announcements
    0.52
    statement
    0.50
    release
    0.50
    Activations Density 0.079%

    No Known Activations