Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11062
    Prev
    Next
    INDEX
    Explanations

    the word "from"

    oai_token-act-pair · gemini-2.0-flash

    phrases starting with 'From'

    np_token-act-pair-logits · gpt-4o-mini

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    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
    通り
    -0.43
    NonNull
    -0.39
     époux
    -0.38
    getError
    -0.38
     Sobre
    -0.38
    cual
    -0.38
    dende
    -0.38
    alat
    -0.38
    UNA
    -0.38
     blandt
    -0.38
    POSITIVE LOGITS
     propOrder
    0.84
     <>",
    0.78
    hdashline
    0.74
    UnsafeEnabled
    0.72
    StoryboardSegue
    0.72
     Infórmanos
    0.71
    IsContent
    0.68
    quelize
    0.66
    webElementXpaths
    0.65
    /***/
    0.64
    Activations Density 0.827%

    No Known Activations