© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14394
    Prev
    Next
    INDEX
    Explanations

    mentions of 'imishment' or derivatives related to the concept of deprivation or reduction

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atother
    -0.53
    penny
    -0.51
     counter
    -0.50
    الحياه
    -0.50
    pool
    -0.48
     actionMode
    -0.48
     thủ
    -0.47
    counter
    -0.47
    Counter
    -0.47
     _$
    -0.47
    POSITIVE LOGITS
    ishment
    4.22
    ishments
    2.08
    ISHMENT
    1.48
    ishing
    0.96
    ished
    0.84
    :✨
    0.72
    GeoNames
    0.69
     punishment
    0.68
    Personendaten
    0.66
    ISHING
    0.62
    Activations Density 0.000%

    No Known Activations