© 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. 14463
    Prev
    Next
    INDEX
    Explanations

    terms related to the PAR gene or its associated characteristics

    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
     purpoſe
    -0.94
     Roskov
    -0.92
     Aoki
    -0.87
     wireType
    -0.87
    AutoScaleMode
    -0.82
    ſelf
    -0.81
     deſt
    -0.81
     poffe
    -0.80
    waist
    -0.80
     Drake
    -0.78
    POSITIVE LOGITS
    par
    1.42
     PAR
    1.34
     Par
    1.27
    Par
    1.26
    PAR
    1.26
     par
    1.25
     Parrish
    1.15
     Parra
    1.12
     Paro
    1.06
     Parry
    1.05
    Activations Density 0.030%

    No Known Activations