© 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. 22-RES-MATRYOSHKA-DC
    7. 820
    Prev
    Next
    INDEX
    Explanations

    German sentences containing modal verbs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     Económica
    -1.29
     Monfieur
    -1.13
     Urbano
    -1.11
     Mejía
    -1.09
     Moisés
    -1.08
     Constitucional
    -1.05
     Darío
    -1.03
     Dijo
    -1.02
     Lázaro
    -1.02
     purpoſe
    -1.02
    POSITIVE LOGITS
     für
    0.76
     das
    0.71
     zu
    0.70
     der
    0.69
     im
    0.69
     uns
    0.69
     mit
    0.69
     auf
    0.67
     aus
    0.67
     über
    0.65
    Activations Density 0.282%

    No Known Activations