© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ample," indicating it is looking for references to sufficiency or abundance

    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
     GenerationType
    -0.70
    adpleegd
    -0.69
     CURIAM
    -0.69
    Autoritní
    -0.68
     OMITTED
    -0.67
    endphp
    -0.67
     nonUne
    -0.65
     onCreateView
    -0.63
    KURZBESCHREIBUNG
    -0.62
    Personendaten
    -0.61
    POSITIVE LOGITS
     ample
    2.75
     Ample
    2.09
     amply
    1.45
    ample
    1.04
     generous
    0.79
     Plenty
    0.72
     ampio
    0.71
     plentiful
    0.66
    Plenty
    0.65
    AMPLE
    0.65
    Activations Density 0.000%

    No Known Activations