© 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. 98159
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical text

    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
    новниш
    -0.65
    JNIEnv
    -0.65
    StandardCharsets
    -0.59
    äude
    -0.58
     Myron
    -0.58
    astanza
    -0.56
    merzen
    -0.55
    Bibliograf
    -0.53
    سرائيل
    -0.53
    новништво
    -0.52
    POSITIVE LOGITS
    ագրություններ
    0.59
    EndInit
    0.59
     Administrativna
    0.58
    তথ্যসূত্র
    0.55
     sanitaires
    0.52
    IndentedString
    0.52
    SourceChecksum
    0.51
    حوالہ
    0.50
    parsedMessage
    0.50
     campagna
    0.49
    Activations Density 0.000%

    No Known Activations