© 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. 20733
    Prev
    Next
    INDEX
    Explanations

    phrases signaling evidence and logical conclusions, particularly in terms of evaluating different types of evidence in arguments

    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
    RenderAtEndOf
    -0.66
    UnusedPrivate
    -0.62
    utnik
    -0.59
    PreferredItem
    -0.55
     Особенно
    -0.54
    apunov
    -0.52
     MatDialog
    -0.48
    SourceChecksum
    -0.48
     hoofd
    -0.47
    BufferException
    -0.46
    POSITIVE LOGITS
     respectively
    0.61
     autorytatywna
    0.57
    respectively
    0.57
    حوالہ
    0.56
    adaptiveStyles
    0.55
     Regu
    0.54
    pexpr
    0.53
    Gesch
    0.52
    ImageContext
    0.52
    ChildIndex
    0.51
    Activations Density 0.321%

    No Known Activations