© 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. 2993
    Prev
    Next
    INDEX
    Explanations

    basic German words and phrases expressing personal opinions, states, or assumptions

    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
     myſelf
    -1.16
     houſe
    -1.11
     pleaſure
    -1.11
     Majefty
    -1.10
     greateſt
    -1.06
    ſelf
    -1.05
     ſtate
    -1.05
     reaſon
    -1.04
     itſelf
    -1.03
     ſche
    -1.02
    POSITIVE LOGITS
     di
    0.85
     or
    0.84
     d
    0.73
     t
    0.72
    ,
    0.72
     in
    0.72
     le
    0.72
     del
    0.71
     und
    0.70
     est
    0.68
    Activations Density 0.308%

    No Known Activations