© 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. 95086
    Prev
    Next
    INDEX
    Explanations

    names

    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
     itſelf
    -0.67
     myſelf
    -0.67
     Monfieur
    -0.63
    rąg
    -0.63
    midler
    -0.62
     themſelves
    -0.62
     poffible
    -0.62
     himſelf
    -0.61
     theſe
    -0.61
     culturelle
    -0.61
    POSITIVE LOGITS
    FormTagHelper
    0.43
     mat
    0.40
    nmgp
    0.39
     dob
    0.39
     со
    0.39
    Hochspringen
    0.39
     love
    0.38
     popis
    0.38
     blo
    0.37
     smer
    0.37
    Activations Density 0.002%

    No Known Activations