© 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. 22-RES-MATRYOSHKA-DC
    7. 2525
    Prev
    Next
    INDEX
    Explanations

    word fragments formed by splitting words ending in "al" into pieces

    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
    SharedCtor
    -0.49
    GenerationType
    -0.45
    
    -0.42
     Avo
    -0.42
    فحة
    -0.41
     Nugent
    -0.41
    ్
    -0.40
    XmlAccessorType
    -0.40
    cektir
    -0.40
    ungalow
    -0.39
    POSITIVE LOGITS
    als
    1.67
    ally
    1.57
    ality
    1.38
    ALS
    1.32
    alised
    1.27
    alse
    1.27
    AL
    1.27
    ALLY
    1.24
    al
    1.20
    aal
    1.14
    Activations Density 0.341%

    No Known Activations