© 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. 4124
    Prev
    Next
    INDEX
    Explanations

    factors, causes, relations

    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
    SourceChecksum
    -0.83
    TemporalType
    -0.69
     OkHttpClient
    -0.69
     snippetHide
    -0.66
    detectChanges
    -0.66
    SequentialGroup
    -0.63
    stdc
    -0.62
     WebDriverWait
    -0.60
    UserScript
    -0.59
     насељу
    -0.59
    POSITIVE LOGITS
     this
    0.85
    this
    0.61
     these
    0.58
     so
    0.58
     me
    0.56
    ?
    0.54
    .
    0.54
     was
    0.53
     This
    0.52
     này
    0.49
    Activations Density 0.002%

    No Known Activations