© 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. 22-RES-MATRYOSHKA-DC
    7. 2667
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems along with the terminology used when stating and proving them

    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.22.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.22.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
     snippetHide
    -0.88
    msgTypes
    -0.78
    HasForeignKey
    -0.75
    #+#
    -0.72
    abestanden
    -0.67
    featureID
    -0.66
    bewerken
    -0.60
    
    -0.60
    zzleHttp
    -0.60
    writeFieldEnd
    -0.58
    POSITIVE LOGITS
     follow
    1.72
     follows
    1.70
    follow
    1.58
     Follow
    1.58
    Follow
    1.55
    follows
    1.42
     FOLLOW
    1.41
    FOLLOW
    1.23
     Follows
    1.20
     folgt
    1.09
    Activations Density 0.218%

    No Known Activations