© 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. 22998
    Prev
    Next
    INDEX
    Explanations

    words that describe negative or harmful attributes

    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
     pleaſure
    -1.23
     ſta
    -1.13
     houſe
    -1.12
     Majefty
    -1.11
     Efq
    -1.11
     lyre
    -1.10
     fermés
    -1.07
    stateProvider
    -1.05
     ſtre
    -1.04
     définiti
    -1.04
    POSITIVE LOGITS
    ness
    1.30
    ous
    1.09
    IOUS
    1.01
    ious
    0.90
    acious
    0.84
    EROUS
    0.84
    icious
    0.82
    rious
    0.80
    dious
    0.77
    s
    0.77
    Activations Density 0.072%

    No Known Activations