© 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. 12-RES-MATRYOSHKA-DC
    7. 12277
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    пня
    -0.47
    utnant
    -0.46
     szóci
    -0.45
     caseros
    -0.44
     Meksika
    -0.41
    jface
    -0.41
    ❋
    -0.41
     ogóle
    -0.40
     corrispond
    -0.40
     Varsity
    -0.39
    POSITIVE LOGITS
    日閲覧
    0.93
     Signalez
    0.81
     Normdatei
    0.80
    Попис
    0.79
    Sucesor
    0.78
    tonsoft
    0.76
    +#+#
    0.73
    HideFlags
    0.73
    ValueStyle
    0.72
    Diweddarwch
    0.71
    Activations Density 0.017%

    No Known Activations