© 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. 0-RES-MATRYOSHKA-DC
    7. 11928
    Prev
    Next
    INDEX
    Explanations

    references to specific fossil groups or taxonomic classifications

    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
     Audiodateien
    -0.67
     pij
    -0.57
    AndEndTag
    -0.52
     Cavendish
    -0.52
    Revenir
    -0.50
     MUNICIP
    -0.50
     FormGroup
    -0.50
     MainAxisSize
    -0.49
    RefNanny
    -0.48
    rante
    -0.48
    POSITIVE LOGITS
    tae
    2.02
    iae
    1.92
    rae
    1.65
    hae
    1.59
    lae
    1.59
    chae
    1.56
    dae
    1.50
    nae
    1.45
    inae
    1.41
    bae
    1.40
    Activations Density 0.003%

    No Known Activations