© 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. 1340
    Prev
    Next
    INDEX
    Explanations

    instances of temporal transitions in narratives

    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
     propOrder
    -0.71
     Rolf
    -0.70
    Rolf
    -0.70
    ']?>
    -0.68
     BorderRadius
    -0.68
    емость
    -0.66
    }';
    -0.66
     gainera
    -0.66
    })]
    -0.66
     Audiodateien
    -0.64
    POSITIVE LOGITS
     During
    1.30
    During
    1.29
    during
    1.29
     during
    1.13
     DURING
    1.13
    durante
    1.13
     Durante
    1.07
     Lors
    1.01
    Lors
    0.99
     durant
    0.98
    Activations Density 0.204%

    No Known Activations