© 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. 23898
    Prev
    Next
    INDEX
    Explanations

    claims about high energy costs and blame for those costs

    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
     favor
    -0.89
     față
    -0.84
     favorably
    -0.84
     neighbor
    -0.83
     rumor
    -0.82
     FAVOR
    -0.82
    neighborhood
    -0.82
     rumors
    -0.81
    neighbor
    -0.81
     neighborhoods
    -0.81
    POSITIVE LOGITS
     organisations
    0.85
     organisers
    0.84
     apologise
    0.83
     Organisations
    0.80
     organisation
    0.77
    Whilst
    0.77
     maths
    0.76
     standardised
    0.76
     realises
    0.75
    Cllr
    0.74
    Activations Density 0.350%

    No Known Activations