© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28539
    Prev
    Next
    INDEX
    Explanations

    references to excuses and justifications

    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
    AutoScaleMode
    -0.71
     transfé
    -0.70
    joueurs
    -0.69
     بيها
    -0.68
    httphttps
    -0.68
     createSlice
    -0.67
    >{@
    -0.66
    PreferredItem
    -0.66
    Waters
    -0.65
     numberOfRows
    -0.65
    POSITIVE LOGITS
    excuse
    1.22
     excuse
    1.14
     excuses
    1.09
     excus
    0.95
    cuses
    0.91
     Excuse
    0.88
     excused
    0.85
     exc
    0.84
    Excuse
    0.77
    cuse
    0.73
    Activations Density 0.005%

    No Known Activations