© 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. 18-RES-MATRYOSHKA-DC
    7. 394
    Prev
    Next
    INDEX
    Explanations

    words that could be used in opinionated writing, such as adjectives and verbs with negative connotations

    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.18.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.18.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
     persoane
    -0.60
     personen
    -0.57
     gesteld
    -0.56
    bilidad
    -0.55
    enumi
    -0.55
     persons
    -0.52
     speciali
    -0.50
    persons
    -0.50
    sizlik
    -0.50
    innen
    -0.49
    POSITIVE LOGITS
     proverbial
    0.74
     tossed
    0.68
    wixt
    0.67
    NameInMap
    0.64
     metaphorical
    0.63
     outta
    0.63
     betwixt
    0.60
    دانشنامهٔ
    0.60
    FileDescriptor
    0.60
    RLock
    0.60
    Activations Density 3.830%

    No Known Activations