© 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. 1139
    Prev
    Next
    INDEX
    Explanations

    references to goals, aims, objects, targets, objectives, and purposes of research and inventions

    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
    uxxxx
    -0.51
    cayaan
    -0.49
    ExceptionHandler
    -0.47
    Chances
    -0.45
    getDrawable
    -0.44
    ruma
    -0.44
    RUnlock
    -0.43
    umat
    -0.42
    ніципалі
    -0.42
     utafitiHapana
    -0.42
    POSITIVE LOGITS
     goal
    2.69
     goals
    2.45
     purpose
    2.41
     objectives
    2.38
     aim
    2.36
    goal
    2.31
     objective
    2.23
     aims
    2.16
     Goals
    2.11
     Goal
    2.08
    Activations Density 1.608%

    No Known Activations