© 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. 93875
    Prev
    Next
    INDEX
    Explanations

    process

    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
    ToPoint
    -0.56
    rawDesc
    -0.54
    ULATE
    -0.54
    脚注の使い方
    -0.53
    handed
    -0.52
     يتيمه
    -0.52
    phazard
    -0.52
    estimm
    -0.52
    XmlAccessorType
    -0.51
     oublié
    -0.51
    POSITIVE LOGITS
     power
    0.65
     Power
    0.57
    ftagPool
    0.56
    Power
    0.51
    FilterChain
    0.50
    rungsseite
    0.48
    Scénario
    0.46
    IVEREF
    0.46
     bý
    0.46
    CDATA
    0.46
    Activations Density 0.005%

    No Known Activations