© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39906
    Prev
    Next
    INDEX
    Explanations

    standalone

    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
     dissemination
    -1.09
     Samos
    -0.65
    Balas
    -0.63
    bership
    -0.58
    share
    -0.57
    ámb
    -0.57
     "..\..\..\
    -0.57
    minton
    -0.57
    SHARE
    -0.55
     pyrolysis
    -0.55
    POSITIVE LOGITS
    \}^{
    0.56
    \}=
    0.55
    Kontrola
    0.50
    GeoNames
    0.49
    IBOutlet
    0.49
    oblotting
    0.48
    ungkinan
    0.46
    CGContext
    0.46
    RTCK
    0.45
    >`;
    0.44
    Activations Density 0.080%

    No Known Activations