© 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. 26612
    Prev
    Next
    INDEX
    Explanations

    terms related to relief or reduction of difficulty

    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
    ruptcy
    -0.82
    anguard
    -0.78
    Portale
    -0.78
    oque
    -0.76
    FieldBuilder
    -0.76
     Ipswich
    -0.71
    runchy
    -0.71
    gridx
    -0.70
     Dzi
    -0.69
    UnitTesting
    -0.69
    POSITIVE LOGITS
     relieved
    0.93
     Ease
    0.86
     eased
    0.84
     ease
    0.82
    Ease
    0.81
     easing
    0.81
     eases
    0.80
     relieving
    0.79
    easing
    0.77
     relieves
    0.77
    Activations Density 0.020%

    No Known Activations