© 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. 93637
    Prev
    Next
    INDEX
    Explanations

    internet

    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
    httphttps
    -0.67
     Chwiliwch
    -0.66
    adaptiveStyles
    -0.63
    providedIn
    -0.62
     Völ
    -0.60
    
    -0.60
    izr
    -0.58
    argout
    -0.57
    Datuak
    -0.57
     RPG
    -0.55
    POSITIVE LOGITS
    COUVER
    0.43
    mulos
    0.42
     West
    0.42
    CWE
    0.41
     Westen
    0.41
    zarchiwizowane
    0.40
    ModelSerializer
    0.40
    ellingham
    0.39
    West
    0.39
    acyj
    0.38
    Activations Density 0.005%

    No Known Activations