© 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. 19
    Prev
    Next
    INDEX
    Explanations

    conversational text

    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
    esanan
    -0.54
    "><?
    -0.53
    ajiban
    -0.49
    choly
    -0.49
    apunov
    -0.48
    sitis
    -0.48
    "><?=
    -0.48
    }>{
    -0.48
    aternion
    -0.47
    unicaciones
    -0.46
    POSITIVE LOGITS
     they
    3.80
     them
    3.55
     They
    3.23
    They
    3.17
     mereka
    3.14
    they
    2.94
     their
    2.83
    他们
    2.67
     Mereka
    2.55
    他們
    2.53
    Activations Density 8.674%

    No Known Activations