© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8356
    Prev
    Next
    INDEX
    Explanations

    the name "Tim" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     Wład
    -0.86
     asy
    -0.80
     Electra
    -0.76
     IRB
    -0.75
    er
    -0.70
     Renegade
    -0.70
    piram
    -0.69
    gameserver
    -0.69
     PWN
    -0.68
     Balfour
    -0.68
    POSITIVE LOGITS
     TIM
    1.53
     Tim
    1.44
    TIM
    1.33
    Tim
    1.20
    imothy
    1.18
     tim
    1.11
     Timothy
    0.91
    tim
    0.89
    timb
    0.85
     Timor
    0.84
    Activations Density 0.003%

    No Known Activations