© 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. 0-CLT-HP
    7. 41468
    Prev
    Next
    INDEX
    Explanations

    is

    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
     open
    -0.65
     Open
    -0.61
     Ste
    -0.51
     Group
    -0.49
     OPEN
    -0.49
     F
    -0.49
     “
    -0.48
     ‘
    -0.48
     We
    -0.48
     st
    -0.48
    POSITIVE LOGITS
    StoryboardSegue
    0.98
     שוליים
    0.93
     betweenstory
    0.90
     myſelf
    0.84
    AndEndTag
    0.82
     leaſt
    0.82
     صوتيه
    0.81
     kasarigan
    0.81
    ſelf
    0.80
     purpoſe
    0.80
    Activations Density 0.139%

    No Known Activations