© 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. 2-RES-MATRYOSHKA-DC
    7. 7130
    Prev
    Next
    INDEX
    Explanations

    references to battery technology and lithium-based energy storage systems

    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
    };*/
    -0.62
     Melville
    -0.61
     Miko
    -0.60
    DockStyle
    -0.59
     Orville
    -0.59
     OBO
    -0.59
     становника
    -0.57
    })`
    -0.57
     gynhyrchwyd
    -0.57
    nologue
    -0.56
    POSITIVE LOGITS
     battery
    3.59
     Battery
    3.36
     batteries
    3.30
    Battery
    3.13
    battery
    3.08
     Batteries
    3.02
     BATTERY
    2.95
    Batteries
    2.80
     batterie
    2.56
    BATTERY
    2.42
    Activations Density 0.016%

    No Known Activations