© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91761
    Prev
    Next
    INDEX
    Explanations

    blood/cells

    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
    ειν
    -0.48
    ่อย
    -0.46
    era
    -0.42
    acha
    -0.41
    ley
    -0.41
    tionally
    -0.41
    ulg
    -0.41
     Def
    -0.40
    ling
    -0.40
    ubis
    -0.40
    POSITIVE LOGITS
     avoient
    0.91
     étoient
    0.84
    AsUp
    0.82
     متحده
    0.75
     auroit
    0.74
     Efq
    0.74
    EndGlobalSection
    0.71
     فريبيس
    0.70
    ThroughAttribute
    0.70
    WithMany
    0.70
    Activations Density 0.006%

    No Known Activations