© 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. 4-CLT-HP
    7. 1608
    Prev
    Next
    INDEX
    Explanations

    be

    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
    glGet
    -0.51
     aveva
    -0.51
    ież
    -0.50
    েকে
    -0.50
    indor
    -0.47
     avendo
    -0.47
    VStack
    -0.47
     tells
    -0.46
    Which
    -0.46
    }}_{\
    -0.45
    POSITIVE LOGITS
     a
    0.88
     an
    0.80
     one
    0.67
     another
    0.63
     motivo
    0.59
     yet
    0.55
     such
    0.55
     something
    0.54
    yntaxException
    0.54
     my
    0.53
    Activations Density 0.005%

    No Known Activations