© 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. 13807
    Prev
    Next
    INDEX
    Explanations

    studied

    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
     estekak
    -0.62
     insuffisamment
    -0.55
    SourceChecksum
    -0.55
    makeConstraints
    -0.55
     متعلقه
    -0.55
    rungsseite
    -0.54
     refroid
    -0.52
    XtraGrid
    -0.50
    balleur
    -0.49
     relâche
    -0.48
    POSITIVE LOGITS
    évaluateur
    0.83
     Efq
    0.61
    ſelf
    0.58
     createSprite
    0.55
     imago
    0.53
    ſelves
    0.53
     RSSSF
    0.52
     meriva
    0.51
     reindeer
    0.51
     domes
    0.51
    Activations Density 0.045%

    No Known Activations