© 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. 1-RES-MATRYOSHKA-DC
    7. 1152
    Prev
    Next
    INDEX
    Explanations

    references to the geographic location California or the city Carlsbad

    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
     @"/
    -0.68
     Италијани
    -0.62
    ggior
    -0.56
    anthemum
    -0.55
    GIVEREF
    -0.54
    География
    -0.54
    RuleContext
    -0.54
     Ira
    -0.53
    UObject
    -0.53
    Życiorys
    -0.52
    POSITIVE LOGITS
     CA
    3.55
    CA
    3.39
     Ca
    3.02
    Ca
    2.94
    ca
    2.81
     ca
    2.75
     calcium
    1.85
     Calcium
    1.67
     Calif
    1.65
    calcium
    1.65
    Activations Density 0.233%

    No Known Activations