© 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. 1-CLT-HP
    7. 12025
    Prev
    Next
    INDEX
    Explanations

    smells

    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
     fragrant
    -0.91
     aromatic
    -0.69
     Aromatic
    -0.64
    ppuden
    -0.60
     väli
    -0.58
    ful
    -0.58
    vaného
    -0.57
    Референце
    -0.57
    Frag
    -0.56
     beginnetje
    -0.55
    POSITIVE LOGITS
    velocityX
    0.57
    LError
    0.53
    herself
    0.52
    SequentialGroup
    0.50
    JsonFormat
    0.49
     herself
    0.48
     correctes
    0.47
    toArray
    0.44
     globe
    0.43
    ں
    0.43
    Activations Density 0.014%

    No Known Activations