© 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. 93441
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    ]--;
    -0.81
    psack
    -0.66
    />";
    -0.63
    mehl
    -0.63
     />";
    -0.59
    SourceChecksum
    -0.59
     Manfaat
    -0.58
    frå
    -0.58
     صوتيه
    -0.58
    Erfolge
    -0.57
    POSITIVE LOGITS
     by
    0.67
    BeginInit
    0.50
     sometime
    0.45
     earlier
    0.44
     Tuesday
    0.44
     especially
    0.42
    AsStream
    0.42
     Wednesday
    0.41
     when
    0.41
    andReturn
    0.41
    Activations Density 0.001%

    No Known Activations