© 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. 24-RES-MATRYOSHKA-DC
    7. 1296
    Prev
    Next
    INDEX
    Explanations

    instances where someone/something is assessing a situation to make decisions

    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.24.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.24.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
     Whilst
    -1.71
    Whilst
    -1.66
     whilst
    -1.42
     twenty
    -1.12
     FUCKING
    -1.09
     fucking
    -1.08
     eighteen
    -1.07
     forty
    -1.05
     seventeen
    -1.05
     Fucking
    -1.05
    POSITIVE LOGITS
     Sept
    0.82
     ''
    0.78
     —
    0.77
     Wednesday
    0.77
     Thursday
    0.76
     Tuesday
    0.75
    Sept
    0.75
    Fig
    0.74
     --
    0.73
     Gov
    0.72
    Activations Density 2.013%

    No Known Activations