© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14103
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "rot" or its spelling variations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vulgaires
    -0.62
    Дереккөздер
    -0.60
    Sucesor
    -0.58
    RTLI
    -0.57
    WriteAttribute
    -0.56
    AndEndTag
    -0.56
    seamless
    -0.55
    دانشنامهٔ
    -0.53
    AutoField
    -0.53
     Chwiliwch
    -0.52
    POSITIVE LOGITS
    rot
    3.09
    ROT
    1.85
    rots
    1.46
    rott
    1.45
    rote
    1.44
    Rot
    1.32
     Rot
    1.21
     rot
    1.20
    rota
    1.07
    rotter
    0.98
    Activations Density 0.004%

    No Known Activations