© 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. 41587
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     [&
    -0.60
    ]]:
    -0.60
    gole
    -0.59
     OMITBAD
    -0.59
     <<<<<<<<<<<<<<
    -0.58
    StoryboardSegue
    -0.58
     vettoriale
    -0.57
    rungsseite
    -0.57
     stedet
    -0.56
     Ressource
    -0.56
    POSITIVE LOGITS
    UnitTesting
    0.56
    
    0.52
    TemporalType
    0.51
    ANTLR
    0.50
    áñez
    0.49
     indent
    0.49
    urtstag
    0.49
    низ
    0.48
     Arce
    0.46
     Vrbo
    0.44
    Activations Density 1.876%

    No Known Activations