© 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. 18-RES-MATRYOSHKA-DC
    7. 36
    Prev
    Next
    INDEX
    Explanations

    sentences expressing doubt or disagreement

    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.18.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.18.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
     ſeveral
    -0.77
     tambi
    -0.62
     fhort
    -0.61
    almost
    -0.60
     tantôt
    -0.58
     ſome
    -0.57
     piuttosto
    -0.56
    сього
    -0.55
     zamiast
    -0.55
     pleaſure
    -0.55
    POSITIVE LOGITS
     necessarily
    1.49
     yet
    1.23
     anymore
    1.09
    necessarily
    1.05
     any
    1.03
     necesariamente
    1.01
     Yet
    0.97
     really
    0.96
     necessariamente
    0.93
    Yet
    0.93
    Activations Density 3.164%

    No Known Activations