© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4830
    Prev
    Next
    INDEX
    Explanations

    references to intervention strategies or programs

    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
     inter
    -0.70
     Inter
    -0.65
    Inter
    -0.61
    AnimationFrame
    -0.58
    inters
    -0.57
    scalatest
    -0.56
    žite
    -0.56
    InstanceState
    -0.56
     useHistory
    -0.55
     aérea
    -0.54
    POSITIVE LOGITS
     intervention
    3.08
    intervention
    2.72
     Intervention
    2.70
     interventions
    2.59
    Intervention
    2.55
     Interventions
    2.34
     intervene
    2.16
     intervened
    1.99
    Interventions
    1.98
     intervención
    1.80
    Activations Density 0.067%

    No Known Activations