© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40709
    Prev
    Next
    INDEX
    Explanations

    publishing

    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
     المعيارى
    -0.79
     мѣ
    -0.77
    writeField
    -0.73
    Recommended
    -0.71
     Италијани
    -0.71
     demanded
    -0.69
    AndEndTag
    -0.66
    erequisite
    -0.66
    SequentialGroup
    -0.66
    yntaxException
    -0.66
    POSITIVE LOGITS
    HideInInspector
    0.53
    StartCoroutine
    0.49
     attitude
    0.45
    b
    0.42
    cout
    0.42
    ENTI
    0.41
     goal
    0.40
    attitude
    0.40
     stretch
    0.40
     limited
    0.40
    Activations Density 1.724%

    No Known Activations