© 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. 1100
    Prev
    Next
    INDEX
    Explanations

    the word "not", and words ending in 't', often both in the same phrase

    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
     be
    -2.41
    be
    -1.59
     Be
    -1.47
    Be
    -1.43
     soient
    -1.40
     puissent
    -1.20
     BE
    -1.13
     sejam
    -1.08
     siano
    -1.04
     бъдат
    -1.00
    POSITIVE LOGITS
     seem
    0.94
    seem
    0.84
    ThroughAttribute
    0.82
    LookAnd
    0.73
     deserve
    0.72
     need
    0.69
     belong
    0.69
     Seem
    0.68
     unknownFields
    0.65
     appear
    0.64
    Activations Density 0.252%

    No Known Activations