© 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. 29727
    Prev
    Next
    INDEX
    Explanations

    terms related to powerlessness and strength

    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
     betweenstory
    -0.57
     BioLib
    -0.56
    onedDateTime
    -0.54
    Glej
    -0.53
     specular
    -0.53
     continuation
    -0.52
    ington
    -0.50
    continuation
    -0.49
    ClCompile
    -0.48
     finer
    -0.48
    POSITIVE LOGITS
     powerless
    1.16
     impotent
    1.01
     power
    0.91
     powerful
    0.91
     Powerful
    0.88
     helplessness
    0.87
    powerful
    0.86
     strength
    0.84
    Powerful
    0.84
     helpless
    0.81
    Activations Density 0.134%

    No Known Activations