© 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. 1-CLT-HP
    7. 45604
    Prev
    Next
    INDEX
    Explanations

    environmental damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.04
    MemoryWarning
    -0.67
    mates
    -0.55
     tartalomajánló
    -0.54
    ful
    -0.54
    agerie
    -0.53
    fuls
    -0.53
    let
    -0.53
    ants
    -0.52
     op
    -0.52
    POSITIVE LOGITS
    oudou
    0.51
     dévelo
    0.49
    Initi
    0.48
    .}\
    0.47
     Initi
    0.47
    ύπ
    0.47
    ItemBackground
    0.47
    kloped
    0.47
     Préférences
    0.46
    ">*</
    0.46
    Activations Density 0.200%

    No Known Activations