© 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. 14288
    Prev
    Next
    INDEX
    Explanations

    references to types of improper or illicit conduct during legal proceedings

    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
     unnecessarily
    -0.84
     unnecessary
    -0.83
     nødvendig
    -0.82
     needlessly
    -0.77
     superfluous
    -0.71
     <=",
    -0.69
    KEYCODE
    -0.68
     notwendi
    -0.68
     مرئيه
    -0.66
     <<<<<<<<<<<<<<
    -0.66
    POSITIVE LOGITS
     improper
    2.27
     Improper
    1.95
    Impro
    1.46
    impro
    1.41
     improperly
    1.29
     impropri
    0.80
     IMPRO
    0.79
     mish
    0.54
     impro
    0.50
     esti
    0.48
    Activations Density 0.003%

    No Known Activations