© 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. 2-RES-MATRYOSHKA-DC
    7. 4118
    Prev
    Next
    INDEX
    Explanations

    mathematical relations and structures

    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
     виправивши
    -0.85
     оригіналу
    -0.82
    Chham
    -0.79
    findpost
    -0.79
    AxisAlignment
    -0.75
    IonicModule
    -0.75
     BoxFit
    -0.73
     تانيه
    -0.71
    Geplaatst
    -0.71
    SpringRunner
    -0.71
    POSITIVE LOGITS
     relation
    2.16
     Relation
    1.96
    relation
    1.92
    Relation
    1.71
     relations
    1.70
     Relations
    1.60
    relations
    1.49
     RELATIONS
    1.41
    Relations
    1.38
     RELATION
    1.03
    Activations Density 0.017%

    No Known Activations