© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2563
    Prev
    Next
    INDEX
    Explanations

    detectable signatures of slow neutrons amidst background noise

    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
    Negative Logits
     "");
    -0.68
    ">{{$
    -0.67
     féd
    -0.67
     grunn
    -0.65
    `;
    -0.64
     rénovation
    -0.64
     råd
    -0.63
     conquête
    -0.63
     Jefus
    -0.63
     Romains
    -0.62
    POSITIVE LOGITS
     signature
    3.31
     signatures
    3.03
    signature
    2.91
     Signature
    2.81
     Signatures
    2.77
    Signature
    2.64
     SIGNATURE
    2.48
    signatures
    2.44
    Signatures
    2.30
    SIGNATURE
    2.08
    Activations Density 0.004%

    No Known Activations