© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14343
    Prev
    Next
    INDEX
    Explanations

    side

    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
    zuführen
    -0.60
    xiety
    -0.50
     Efe
    -0.48
     Thyme
    -0.47
    yles
    -0.47
     Coma
    -0.47
    ebrow
    -0.47
    ctable
    -0.46
     considérons
    -0.45
    cium
    -0.45
    POSITIVE LOGITS
    GraphicsUnit
    0.60
    ModelForm
    0.57
    SpringBootTest
    0.55
    imageshack
    0.55
    Nazionale
    0.53
    onAttach
    0.53
     BrowserModule
    0.50
    Einzelnachweise
    0.49
     onData
    0.49
     ComVisible
    0.48
    Activations Density 0.021%

    No Known Activations