© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12122
    Prev
    Next
    INDEX
    Explanations

    Email/code snippets

    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
    orp
    -2.02
    ORP
    -1.20
    Corp
    -0.79
    +#+#
    -0.68
    MessageTagHelper
    -0.63
    يكب
    -0.59
     pinulongan
    -0.58
    Datuak
    -0.58
    المناصب
    -0.56
    BindView
    -0.55
    POSITIVE LOGITS
    eder
    0.51
     Comer
    0.49
    estre
    0.49
     scaricare
    0.47
    roffenen
    0.47
     Sneak
    0.46
     expériment
    0.46
    mtable
    0.45
    der
    0.45
    HostException
    0.45
    Activations Density 0.058%

    No Known Activations