© 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. 90532
    Prev
    Next
    INDEX
    Explanations

    ichord

    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
     Nest
    -0.71
     nahilalakip
    -0.65
     ModelExpression
    -0.63
     esternos
    -0.62
    featureID
    -0.61
     pinulongan
    -0.58
    ichord
    -0.56
     relâche
    -0.56
    Rüyada
    -0.54
     Crossroads
    -0.53
    POSITIVE LOGITS
    led
    0.70
    riel
    0.59
     Courant
    0.58
    ce
    0.52
    zz
    0.51
    go
    0.51
    ors
    0.50
    elsa
    0.50
     Colossus
    0.50
    pos
    0.50
    Activations Density 0.232%

    No Known Activations