© 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. 20917
    Prev
    Next
    INDEX
    Explanations

    phrases indicating readiness or preparedness

    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
    cifix
    -0.81
    XmlAccessType
    -0.72
    verwijspagina
    -0.71
     Manor
    -0.68
     Quinta
    -0.68
     Catawiki
    -0.67
    Pyx
    -0.65
    neux
    -0.65
    MigrationBuilder
    -0.64
    /$',
    -0.64
    POSITIVE LOGITS
     Ready
    1.60
     ready
    1.52
    ready
    1.38
    Ready
    1.38
     READY
    1.38
    READY
    1.33
     readiness
    0.95
    isReady
    0.90
    onReady
    0.89
     гото
    0.88
    Activations Density 0.012%

    No Known Activations