© 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. 28618
    Prev
    Next
    INDEX
    Explanations

    terms related to mammals

    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
    bootstrapcdn
    -0.64
    </i>
    -0.61
    kit
    -0.60
     kit
    -0.58
    Kirsten
    -0.57
    Irene
    -0.57
     Greenwood
    -0.55
     judiciaire
    -0.54
    Eph
    -0.53
     zboží
    -0.53
    POSITIVE LOGITS
     Mammals
    1.49
     mammals
    1.45
     Mammal
    1.41
     mammal
    1.27
    mamm
    1.26
    Mammal
    1.24
     mammalian
    1.12
    Mam
    1.09
     MAM
    1.08
     Mam
    1.05
    Activations Density 0.003%

    No Known Activations