© 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. 593
    Prev
    Next
    INDEX
    Explanations

    words or short names that start with "jo", "ko", or "ho" or contain the letters "AO"

    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
    ly
    -1.09
    ness
    -0.99
    に
    -0.98
    了
    -0.91
    men
    -0.85
    nya
    -0.83
    mos
    -0.82
    mente
    -0.81
    ting
    -0.81
    ۰
    -0.80
    POSITIVE LOGITS
    gether
    0.42
    脚注の使い方
    0.38
    equipment
    0.36
    vernight
    0.35
    los
    0.35
    sso
    0.35
    pportun
    0.34
     scorso
    0.34
    event
    0.34
    ArgsConstructor
    0.34
    Activations Density 0.750%

    No Known Activations