© 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. 4196
    Prev
    Next
    INDEX
    Explanations

    able

    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
    getting
    -0.57
     getting
    -0.55
     uncovering
    -0.52
    making
    -0.51
     forming
    -0.50
     proving
    -0.50
     accessing
    -0.49
    rzost
    -0.48
     making
    -0.48
     completing
    -0.47
    POSITIVE LOGITS
    LookAnd
    0.81
     estekak
    0.67
    SequentialGroup
    0.66
    NameInMap
    0.66
    stdc
    0.63
    ########.
    0.63
    XmlAccessType
    0.62
     المعيارى
    0.62
    
    0.60
     utafitiHapana
    0.59
    Activations Density 0.006%

    No Known Activations