© 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. 92999
    Prev
    Next
    INDEX
    Explanations

    effectiveness

    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
    发表于
    -0.65
     calendriers
    -0.57
    효
    -0.54
    Autoritní
    -0.53
    效
    -0.53
     دیکھیے
    -0.48
     efficiencies
    -0.48
    geset
    -0.48
     effects
    -0.45
     effect
    -0.45
    POSITIVE LOGITS
     for
    0.61
     Waray
    0.60
     in
    0.59
     betweenstory
    0.59
    TemporalType
    0.57
    tvguidetime
    0.57
     kautta
    0.55
    MemoryWarning
    0.54
    ApiProperty
    0.54
    providedIn
    0.53
    Activations Density 0.002%

    No Known Activations