© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5092
    Prev
    Next
    INDEX
    Explanations

    references to a biblical figure associated with a divine promise and the ladder connecting earth and heaven

    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
     šķ
    -0.56
    bentar
    -0.49
    ॠ
    -0.46
     promptly
    -0.45
     Añade
    -0.43
     çap
    -0.43
    тивной
    -0.42
     lieto
    -0.41
    zyb
    -0.40
     Príncipe
    -0.40
    POSITIVE LOGITS
     الحره
    0.76
    ]")]
    0.75
     '\\;'
    0.75
    AutoScale
    0.74
    TintMode
    0.72
    AddTagHelper
    0.72
    ="#"><
    0.72
     onAnimation
    0.71
    Pratique
    0.71
    ModelAdmin
    0.71
    Activations Density 1.134%

    No Known Activations