© 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. 23
    Prev
    Next
    INDEX
    Explanations

    instances of trying to do something or an ability to do something.

    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
     mourut
    -1.26
     étoit
    -1.24
     auroit
    -1.20
     feroit
    -1.05
     giudi
    -1.03
     avoient
    -1.03
     réguli
    -1.02
     ſeveral
    -1.02
     médicaux
    -1.02
     poffible
    -1.02
    POSITIVE LOGITS
     make
    1.45
     get
    1.34
     take
    1.34
     create
    1.27
     give
    1.23
     keep
    1.23
     bring
    1.21
     put
    1.20
     do
    1.16
     provide
    1.16
    Activations Density 4.169%

    No Known Activations