© 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. 11939
    Prev
    Next
    INDEX
    Explanations

    expressions of confidence and encouragement related to self-assurance and well-being

    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
    ########.
    -0.87
    Legături
    -0.57
    ichteten
    -0.56
     actionPerformed
    -0.54
    styleable
    -0.54
     Numerade
    -0.53
    Życiorys
    -0.52
    toMatchSnapshot
    -0.50
    цездатний
    -0.50
    +#+
    -0.50
    POSITIVE LOGITS
    Trust
    0.76
     entrust
    0.76
     trust
    0.75
     reassuring
    0.75
    trust
    0.72
    安心
    0.71
     trusting
    0.71
     dependable
    0.70
     reassured
    0.69
     Trust
    0.68
    Activations Density 0.059%

    No Known Activations