© 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. 29709
    Prev
    Next
    INDEX
    Explanations

    phrases related to poses and representations of child abuse

    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
    хьтан
    -0.98
    CONSIN
    -0.97
    Ivo
    -0.96
    contentLoaded
    -0.93
     Verdun
    -0.90
    GEBURTSDATUM
    -0.86
    SBATCH
    -0.85
    hyrchwyd
    -0.85
     GenerationType
    -0.83
    -------------</
    -0.83
    POSITIVE LOGITS
     pose
    1.55
     Pose
    1.50
     poses
    1.48
     posed
    1.47
    Pose
    1.47
     posing
    1.40
    pose
    1.29
     posé
    0.92
     poser
    0.88
    POSE
    0.86
    Activations Density 0.007%

    No Known Activations