© 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. 22-RES-MATRYOSHKA-DC
    7. 1462
    Prev
    Next
    INDEX
    Explanations

    sequences of the form "När[hä]lsan ..."

    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
    ')))
    -0.65
    Controllo
    -0.57
    Personensuche
    -0.56
    writeFieldEnd
    -0.56
     varandra
    -0.56
    ")))
    -0.55
    Portale
    -0.55
    __':
    -0.54
    _))
    -0.52
    '}}>
    -0.51
    POSITIVE LOGITS
     Diſ
    0.88
     Reſ
    0.88
     Chriftian
    0.87
     Conſ
    0.86
     Majefty
    0.82
     Inſ
    0.81
     Anſ
    0.77
     purpoſe
    0.77
     Theſe
    0.76
     ſtate
    0.75
    Activations Density 0.079%

    No Known Activations