© 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. 14757
    Prev
    Next
    INDEX
    Explanations

    references to water-related topics

    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
     myſelf
    -1.09
     itſelf
    -0.97
     Monfieur
    -0.96
    protoimpl
    -0.92
     Majefty
    -0.91
     themſelves
    -0.90
     becauſe
    -0.89
     purpoſe
    -0.88
     Jefus
    -0.87
     pleaſure
    -0.85
    POSITIVE LOGITS
    h
    0.73
    v
    0.71
    V
    0.69
     Zeller
    0.67
    w
    0.66
    Carcinogenicity
    0.65
    Z
    0.65
    z
    0.65
    C
    0.65
    gal
    0.63
    Activations Density 0.024%

    No Known Activations