© 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. 15195
    Prev
    Next
    INDEX
    Explanations

    instances of the word "prohibit" or its variants related to forbidding actions

    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
     Weiden
    -0.65
     avoided
    -0.60
    bane
    -0.60
     Dunne
    -0.60
    évaluateur
    -0.59
    Heer
    -0.59
     Avoidance
    -0.57
    onedDateTime
    -0.57
     circunstan
    -0.55
    updateTime
    -0.55
    POSITIVE LOGITS
     prohibit
    2.55
     prohibits
    2.33
     prohibiting
    1.73
     forbids
    1.57
     forbid
    1.36
     prohibited
    1.20
     forbade
    1.16
     forbidding
    0.99
     prohi
    0.75
     precludes
    0.67
    Activations Density 0.002%

    No Known Activations