© 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. 0-RES-MATRYOSHKA-DC
    7. 12425
    Prev
    Next
    INDEX
    Explanations

    references to the location beside a specific building or landmark

    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
    -0.66
    aarrggbb
    -0.63
     nahilalakip
    -0.57
    حياته
    -0.55
    Tikang
    -0.54
     للمعارف
    -0.54
     AttributeSet
    -0.53
    SequentialGroup
    -0.52
    లాలు
    -0.51
    Распо
    -0.51
    POSITIVE LOGITS
     beside
    2.88
     Beside
    2.48
     accanto
    1.08
     alongside
    1.00
     Alongside
    0.97
     citoy
    0.84
    Alongside
    0.82
     obok
    0.77
    Bes
    0.76
     purpoſe
    0.74
    Activations Density 0.001%

    No Known Activations