© 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. 0-RES-MATRYOSHKA-DC
    7. 12301
    Prev
    Next
    INDEX
    Explanations

    references to the concept of spatial or structural alignment

    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
     itſelf
    -0.70
     againſt
    -0.65
    
    -0.64
     reafon
    -0.63
     hinweg
    -0.62
     perfons
    -0.62
     occafion
    -0.62
    ρεί
    -0.61
     myſelf
    -0.61
    braith
    -0.60
    POSITIVE LOGITS
    Alignment
    2.80
    alignment
    1.56
     Alignment
    1.08
    extAlignment
    0.85
    DockStyle
    0.78
    DeleteBehavior
    0.71
    AxisAlignment
    0.69
    ALIGN
    0.67
    TextAlignment
    0.67
     DialogInterface
    0.62
    Activations Density 0.001%

    No Known Activations