© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14842
    Prev
    Next
    INDEX
    Explanations

    instructions or links related to updating or configuring application settings

    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
    </em>
    -1.44
    <em>
    -0.79
    <strong>
    -0.71
    <h3>
    -0.68
     fl
    -0.65
     first
    -0.58
    <unused63>
    -0.56
     
    -0.55
    """.
    -0.55
    fl
    -0.54
    POSITIVE LOGITS
    </b>
    3.64
    dfrac
    1.14
    <b>
    1.13
    </i>
    1.11
    ']").
    1.07
    '></
    1.05
    "}>
    1.05
    </strong>
    1.01
    ']")
    0.97
    "};
    0.96
    Activations Density 0.001%

    No Known Activations