© 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. 97058
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ViewImports
    -0.64
    Predecesor
    -0.63
     AssemblyTitle
    -0.62
    `,
    -0.62
     bezeichneter
    -0.62
    曖昧さ回避
    -0.61
     postales
    -0.61
     Administrativna
    -0.60
    '}),
    -0.59
     virtuales
    -0.59
    POSITIVE LOGITS
    makeText
    0.58
    accia
    0.53
     cref
    0.48
     “
    0.47
     >=",
    0.46
    ба
    0.44
     "
    0.43
     πρά
    0.41
     OMITTED
    0.41
    PullParser
    0.40
    Activations Density 0.007%

    No Known Activations