© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21998
    Prev
    Next
    INDEX
    Explanations

    mentions of adult entertainment content

    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
    providedIn
    -0.91
     lenker
    -0.90
     MonoBehaviour
    -0.87
    RectangleBorder
    -0.84
    zzleHttp
    -0.83
    帖最后由
    -0.83
    ResumeLayout
    -0.76
    KommentareTeilen
    -0.75
    Tracce
    -0.73
     requestCode
    -0.73
    POSITIVE LOGITS
     Porn
    1.49
    Porn
    1.46
     porn
    1.44
     pornography
    1.31
    porn
    1.29
     porno
    1.04
     DSM
    0.64
     "*",
    0.56
     "));
    0.54
     vind
    0.53
    Activations Density 0.002%

    No Known Activations