© 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. 509
    Prev
    Next
    INDEX
    Explanations

    crawling

    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
     chemins
    -0.59
    may
    -0.51
    Referanser
    -0.50
     المعيارى
    -0.50
    hy
    -0.50
     récemment
    -0.50
    fusc
    -0.50
    χρι
    -0.49
    yam
    -0.49
     frattempo
    -0.49
    POSITIVE LOGITS
     complexes
    0.56
    InSection
    0.54
     scales
    0.51
     aliments
    0.50
     BadRequest
    0.50
    cinia
    0.50
     /\.
    0.49
     SqlConnection
    0.49
     doInBackground
    0.49
     صوتيه
    0.48
    Activations Density 0.036%

    No Known Activations