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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16189
    Prev
    Next
    INDEX
    Explanations

    words related to waste management and disposal

    oai_token-act-pair · gemini-2.0-flash

    gibberish

    np_token-act-pair-logits · gemini-2.0-flash

    waste and garbage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    WithIOException
    -0.69
    Demografie
    -0.66
    Palmar
    -0.65
    IntoConstraints
    -0.65
    uxxxx
    -0.64
    ]--;
    -0.63
    Билгалдахарш
    -0.61
     referrerpolicy
    -0.60
     OMIT
    -0.59
     gynhyrchwyd
    -0.58
    POSITIVE LOGITS
    }{#
    0.50
     lepro
    0.46
     Progressive
    0.45
     offerts
    0.42
     Osten
    0.42
     approche
    0.42
     cerró
    0.42
     vertes
    0.41
     barrera
    0.41
    emploi
    0.41
    Activations Density 1.556%

    No Known Activations