© 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. 92872
    Prev
    Next
    INDEX
    Explanations

    genre, learning

    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
    numerusform
    -0.74
    Personendaten
    -0.72
    )))),
    -0.70
     utafitiHapana
    -0.64
    afficheront
    -0.61
    }}}}
    -0.60
    ']").
    -0.57
    '])->
    -0.56
    SourceChecksum
    -0.56
    WebElementEntity
    -0.55
    POSITIVE LOGITS
    RequestMethod
    0.60
     TextAppearance
    0.59
     magique
    0.52
     esterni
    0.51
     containment
    0.50
    SequentialGroup
    0.50
    IntPtr
    0.50
    WebElement
    0.49
     fapt
    0.49
     înd
    0.49
    Activations Density 0.812%

    No Known Activations