© 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. 384
    Prev
    Next
    INDEX
    Explanations

    words and phrases often used in scientific research papers and technical documentation, especially those detailing a hypothesis and tests or manual updates and fixes

    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
    /**/*.
    -0.51
    Hauptartikel
    -0.49
    äki
    -0.44
    respectively
    -0.40
    arne
    -0.36
    msubsup
    -0.35
    iston
    -0.35
    matically
    -0.35
    toBeDefined
    -0.34
    ੱਕ
    -0.34
    POSITIVE LOGITS
     this
    3.89
    this
    3.08
     questo
    2.25
     этого
    2.22
     THIS
    2.17
     questa
    2.17
    This
    2.14
     này
    2.14
     these
    2.08
     acest
    2.08
    Activations Density 5.711%

    No Known Activations