© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4998
    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
    .
    -0.68
     nahilalakip
    -0.58
     >=",
    -0.51
    فحة
    -0.51
    .:
    -0.50
    :
    -0.49
    whom
    -0.49
     :
    -0.48
    SourceChecksum
    -0.47
    whose
    -0.46
    POSITIVE LOGITS
     saites
    0.63
     geldig
    0.62
    ніципалі
    0.59
     ElementRef
    0.54
    rupulous
    0.53
     July
    0.52
     للمعارف
    0.52
     April
    0.52
     userSchema
    0.52
     May
    0.52
    Activations Density 0.003%

    No Known Activations