© 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. 0-RES-MATRYOSHKA-DC
    7. 11322
    Prev
    Next
    INDEX
    Explanations

    mentions of contraceptive pills or medication

    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
    rungsseite
    -0.64
     виправивши
    -0.60
    ]--;
    -0.59
    .*")]
    -0.58
     Италијани
    -0.55
     <<<<<<<<<<<<<<
    -0.55
    +#+#
    -0.55
    Palmar
    -0.54
     Pod
    -0.53
    basic
    -0.53
    POSITIVE LOGITS
     pill
    3.67
    pill
    2.88
     Pill
    2.80
     pills
    2.45
    Pill
    2.27
    pills
    2.00
     PILL
    1.95
     Pills
    1.87
    piller
    1.02
     pillows
    0.83
    Activations Density 0.001%

    No Known Activations