© 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. 5-CLT-HP
    7. 2017
    Prev
    Next
    INDEX
    Explanations

    technical documents/emails

    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
     Савезне
    -0.71
    ArgsConstructor
    -0.63
    UnsafeEnabled
    -0.63
    Tē
    -0.63
     Meksiku
    -0.60
    CreateModel
    -0.59
     EnglishChoose
    -0.59
     препратки
    -0.59
     kasarigan
    -0.59
    yntaxException
    -0.59
    POSITIVE LOGITS
    providedIn
    0.67
    (&:
    0.58
     finish
    0.48
     soft
    0.46
    sodik
    0.46
     deliver
    0.43
    自信
    0.41
     social
    0.41
     hard
    0.41
     button
    0.40
    Activations Density 0.001%

    No Known Activations