© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    pre- or under- prefixes, as well as words where the ending might not be fully included.

    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
    VersionUID
    -0.65
    ه
    -0.61
    APORE
    -0.60
    __((
    -0.59
    ed
    -0.57
     HasFactory
    -0.56
     صوتيه
    -0.56
    UVWXYZ
    -0.54
    eater
    -0.54
    WebVitals
    -0.54
    POSITIVE LOGITS
    avid
    0.60
    ged
    0.56
    rive
    0.53
    roid
    0.50
    ouble
    0.48
    addy
    0.46
    raw
    0.46
    ded
    0.46
    roids
    0.45
    trial
    0.45
    Activations Density 0.712%

    No Known Activations