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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93001
    Prev
    Next
    INDEX
    Explanations

    Change

    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
     kasarigan
    -0.63
    :+:
    -0.57
    StructEnd
    -0.51
    MessageOf
    -0.51
    Higher
    -0.50
    CDCl
    -0.49
    utzt
    -0.48
    ftagPool
    -0.48
    eniendo
    -0.47
    ⓧ
    -0.47
    POSITIVE LOGITS
     probability
    0.65
     level
    0.61
     likelihood
    0.58
     sense
    0.57
     chance
    0.54
    ervlak
    0.50
     rate
    0.50
     amount
    0.49
     need
    0.49
    wele
    0.48
    Activations Density 0.004%

    No Known Activations