© 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. 11226
    Prev
    Next
    INDEX
    Explanations

    descriptions of molecular or cellular associations, particularly proteins associated with specific biological processes

    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
     defaultstate
    -0.77
    VersionUID
    -0.67
     Evidence
    -0.64
     Administrativna
    -0.62
    Evidence
    -0.60
    evidence
    -0.59
    prefixer
    -0.58
    __).
    -0.58
    IsContent
    -0.57
     evidence
    -0.57
    POSITIVE LOGITS
    associated
    1.65
    Associated
    0.90
    Xna
    0.61
    ConstraintMaker
    0.56
     WaitForSeconds
    0.55
    SBATCH
    0.55
    Дереккөздер
    0.54
    ніципа
    0.54
    beeren
    0.53
    heiser
    0.52
    Activations Density 0.002%

    No Known Activations