© 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. 24-RES-MATRYOSHKA-DC
    7. 468
    Prev
    Next
    INDEX
    Explanations

    negative statements and uncertain qualifications

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     not
    -0.87
    almost
    -0.81
     lenker
    -0.76
     não
    -0.76
     nonetheless
    -0.74
     almost
    -0.73
    somewhat
    -0.73
     también
    -0.71
     ikke
    -0.71
     also
    -0.69
    POSITIVE LOGITS
     necessarily
    1.38
    necessarily
    1.09
     anymore
    1.05
     necessariamente
    1.03
     yet
    1.01
     necesariamente
    1.00
     nécessairement
    0.88
    yet
    0.87
     forcément
    0.84
    Yet
    0.84
    Activations Density 2.116%

    No Known Activations