© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1168
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    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
     saites
    -0.55
     myſelf
    -0.53
    InitVars
    -0.51
    НИК
    -0.51
     Diſ
    -0.50
    Tikang
    -0.50
     ſta
    -0.50
     pleaſure
    -0.50
     houſe
    -0.50
     purpoſe
    -0.49
    POSITIVE LOGITS
     E
    1.20
    E
    1.13
    エ
    0.99
     EP
    0.99
    epsilon
    0.95
     EE
    0.93
     Edward
    0.90
     EF
    0.90
    getE
    0.90
     É
    0.89
    Activations Density 2.040%

    No Known Activations